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

    Neuronpedia

    INDEX
    Explanations

    knowledgeable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Стаўкі
    0.82
     Benin
    0.80
     Biele
    0.80
    UM
    0.79
    HTTPRequest
    0.79
     Гла
    0.79
    crossentropy
    0.78
     interno
    0.77
    mu
    0.76
     Strang
    0.76
    POSITIVE LOGITS
    ד
    1.04
    é
    0.91
    不
    0.91
    ద
    0.90
    d
    0.88
     knowledgeable
    0.87
    ;
    0.85
    ל
    0.85
    де
    0.84
    те
    0.83
    Act Density 0.002%

    No Known Activations