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

    Neuronpedia

    INDEX
    Explanations

    sequences related to programming constructs or code structure

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

    relative paths and code file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pic
    -0.26
     suscripción
    -0.22
    pic
    -0.22
     fam
    -0.21
    Maj
    -0.20
    Awe
    -0.20
    Regression
    -0.20
     sağlık
    -0.19
    ↵
    -0.19
     picado
    -0.19
    POSITIVE LOGITS
    LookAnd
    0.90
    __::
    0.84
    parsedMessage
    0.82
     useAppContext
    0.80
     snippetHide
    0.79
    fromnode
    0.78
     GenerationType
    0.77
    <pad>
    0.76
    [@BOS@]
    0.75
    <unused3>
    0.75
    Act Density 0.028%

    No Known Activations