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

    Neuronpedia

    INDEX
    Explanations

    references to programming or code structure elements

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

    .py or .h files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.83
     ब्रेकडाउन
    -0.73
    RemoveField
    -0.73
    ValueStyle
    -0.66
    styleType
    -0.65
    <unused43>
    -0.65
    <unused14>
    -0.65
    <unused16>
    -0.65
    <unused8>
    -0.65
    [@BOS@]
    -0.65
    POSITIVE LOGITS
     húmedo
    0.30
     ģ
    0.30
    sdag
    0.29
    PARAMETERS
    0.28
     apparaître
    0.28
     conclure
    0.27
    SupportActionBar
    0.26
    </strong>
    0.26
    MAR
    0.25
     pě
    0.25
    Act Density 0.020%

    No Known Activations