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

    Neuronpedia

    INDEX
    Explanations

    books and related information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.47
     markings
    0.46
     colliding
    0.44
    astaan
    0.44
    Stride
    0.43
    กับ
    0.42
    liness
    0.42
    ী
    0.42
    ת
    0.41
    Aspect
    0.41
    POSITIVE LOGITS
     ግራም
    0.55
     کتاب
    0.47
     kitap
    0.46
     otro
    0.46
    書店
    0.45
     buku
    0.44
    艦
    0.44
     ち
    0.43
     hilfre
    0.43
     croit
    0.43
    Act Density 0.006%

    No Known Activations