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

    Neuronpedia

    INDEX
    Explanations

    identifiers and relationship mappings in data structures or query statements

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

    id keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -0.79
    évaluateur
    -0.76
     myſelf
    -0.74
    verifyException
    -0.73
    contentLoaded
    -0.70
     itſelf
    -0.69
    [@BOS@]
    -0.68
    <unused20>
    -0.68
    <unused16>
    -0.68
    <unused14>
    -0.68
    POSITIVE LOGITS
    quelles
    0.33
    指定
    0.31
     tempat
    0.30
     gerekli
    0.30
    ID
    0.30
     interesa
    0.29
    id
    0.29
     priorité
    0.29
     inversiones
    0.29
     Tiefe
    0.29
    Act Density 0.014%

    No Known Activations