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

    Neuronpedia

    INDEX
    Explanations

    passthrough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.52
    .
    1.34
     isotopes
    1.33
     authorizations
    1.32
    '
    1.31
    ।
    1.31
    \
    1.29
     instabilities
    1.27
     of
    1.26
     arrays
    1.26
    POSITIVE LOGITS
    ка
    1.27
    ным
    1.19
     není
    1.16
    و
    1.14
    ар
    1.09
    с
    1.09
    сы
    1.07
    ่า
    1.02
    ستخدم
    1.02
    ষধ
    1.01
    Act Density 0.000%

    No Known Activations