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

    Neuronpedia

    INDEX
    Explanations

    specific actions or processes related to investigation and analysis in various contexts

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

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnknownFieldSet
    -0.53
     AssemblyCulture
    -0.52
    ABETH
    -0.49
     виправивши
    -0.49
    évaluateur
    -0.48
    heets
    -0.48
     Administrativna
    -0.48
    :✨
    -0.47
    yntaxException
    -0.47
    monials
    -0.46
    POSITIVE LOGITS
     chrétiens
    0.47
     capitán
    0.43
     يتيمه
    0.43
     embarazada
    0.42
     enfans
    0.42
     larmes
    0.39
     jefes
    0.39
     jefe
    0.39
     normaux
    0.38
     cristianos
    0.38
    Act Density 0.080%

    No Known Activations