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

    Neuronpedia

    INDEX
    Explanations

    expressions of interesting or noteworthy qualities in various contexts

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

    positive exclamations and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.79
     AssemblyVersion
    -0.69
    OGND
    -0.63
    TypedDataSet
    -0.60
    ArrowToggle
    -0.59
    ValueStyle
    -0.56
     jsPsych
    -0.56
    yntaxException
    -0.56
    ConstraintMaker
    -0.55
    LLocation
    -0.55
    POSITIVE LOGITS
     indeed
    0.64
    !
    0.57
     stuff
    0.55
     konu
    0.48
     kyllä
    0.48
    ですね
    0.48
     how
    0.47
     doesn
    0.46
    !!
    0.46
     nonetheless
    0.46
    Act Density 0.044%

    No Known Activations