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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and calculations

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

    Numbers in mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    huge Pasta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -1.12
     TType
    -0.90
    ThroughAttribute
    -0.86
     propOrder
    -0.85
    MockMvc
    -0.84
    LookAnd
    -0.82
    MethodManager
    -0.77
     Roskov
    -0.77
    tvguidetime
    -0.76
     useAppContext
    -0.75
    POSITIVE LOGITS
     Paper
    0.62
     paper
    0.59
    Paper
    0.57
    mui
    0.50
    paper
    0.49
    Mui
    0.49
     TextField
    0.42
     di
    0.42
    ساب
    0.42
    jss
    0.42
    Act Density 0.144%

    No Known Activations