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

    Neuronpedia

    INDEX
    Explanations

    assignments and comparisons in programming code

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

    key, name, label, value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     パンチラ
    -0.82
    <unused28>
    -0.81
    <unused41>
    -0.81
    <pad>
    -0.81
    <unused8>
    -0.81
    <unused23>
    -0.81
    <unused52>
    -0.81
    <unused14>
    -0.81
    [@BOS@]
    -0.81
    <unused3>
    -0.81
    POSITIVE LOGITS
     value
    0.34
    value
    0.31
    onChangeText
    0.30
    Value
    0.28
    text
    0.25
    wohner
    0.25
    méno
    0.24
     paga
    0.24
    FieldNumber
    0.24
    -
    0.23
    Act Density 0.008%

    No Known Activations