Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that describe enhancements or improvements in visual aesthetics and design features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "to" or "a/an"

    np_acts-logits-general · gemini-2.0-flash

    adding to or enhancing qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AppCompatTheme
    -0.68
     '\\;'
    -0.62
    CppMethod
    -0.55
     GlobalKey
    -0.52
    mities
    -0.52
     souffrance
    -0.51
    ADELPHIA
    -0.51
    windowFixed
    -0.50
    WireFormatLite
    -0.49
    principalColumn
    -0.49
    POSITIVE LOGITS
    writeFieldEnd
    0.62
     visually
    0.60
    oneofs
    0.57
     invokingState
    0.57
    webElementXpaths
    0.54
    esModule
    0.51
     pseudo
    0.51
     BoxFit
    0.49
     jette
    0.49
    semantics
    0.48
    Act Density 0.123%

    No Known Activations