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

    Neuronpedia

    INDEX
    Explanations

    resigned acceptance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.49
    et
    1.45
    at
    1.41
     be
    1.34
    in
    1.31
    ל
    1.28
     do
    1.18
     (
    1.15
    il
    1.13
     by
    1.13
    POSITIVE LOGITS
    ari
    1.29
    '
    1.26
    (
    1.20
    0
    1.20
    ０
    1.18
    𝟬
    1.15
    د
    1.14
    お
    1.10
    д
    1.03
     क्षेत्रा
    1.02
    Act Density 0.001%

    No Known Activations