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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to loops and array operations

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

    structured or technical text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cậu
    -0.30
     sli
    -0.29
     capucha
    -0.28
     pintados
    -0.28
     Sli
    -0.27
     chi̍t
    -0.27
     dziewczyn
    -0.26
     рас
    -0.26
     ralla
    -0.26
     droop
    -0.26
    POSITIVE LOGITS
    PreferredItem
    0.61
     Administrativna
    0.59
     Italijanski
    0.58
    VYMaps
    0.57
     resourceCulture
    0.56
    TypedDataSet
    0.54
    FirstResponder
    0.52
    idemia
    0.52
     surla
    0.52
     ProtoMessage
    0.51
    Act Density 0.034%

    No Known Activations