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

    Neuronpedia

    INDEX
    Explanations

    dialogue and conversational exchanges in the text

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

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.63
     kaarangay
    -0.63
    TypedDataSet
    -0.59
     Biôgrafia
    -0.59
     linkovi
    -0.59
    mergeFrom
    -0.59
    abestanden
    -0.58
    scribers
    -0.56
    KommentareTeilen
    -0.55
    WriteBarrier
    -0.54
    POSITIVE LOGITS
     said
    0.45
     I
    0.42
     he
    0.41
     came
    0.40
    come
    0.39
    Half
    0.39
     comes
    0.39
     Half
    0.38
     the
    0.38
    tu
    0.38
    Act Density 0.011%

    No Known Activations