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

    Neuronpedia

    INDEX
    Explanations

    empty string values

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

    Empty strings in code

    np_acts-logits-general · gemini-2.0-flash

    empty strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ClientSize
    -0.71
    findpost
    -0.69
    es
    -0.67
    Климат
    -0.65
    ات
    -0.64
    ы
    -0.63
     tra
    -0.60
    en
    -0.60
    regon
    -0.59
     Presto
    -0.58
    POSITIVE LOGITS
     ainfi
    0.70
    ",""
    0.67
     vacía
    0.64
     nélk
    0.63
     الاطلاع
    0.63
     Lijst
    0.63
     ""
    0.62
    />
    0.62
     Maul
    0.61
    UnsafeEnabled
    0.61
    Act Density 0.144%

    No Known Activations