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

    Neuronpedia

    INDEX
    Explanations

    Python function definitions for list/file operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -(
    1.20
     (
    1.19
    （
    1.06
    (
    1.02
    (/
    0.98
     [(
    0.97
    -(
    0.96
     ગામ
    0.95
    -(\
    0.95
     (†
    0.93
    POSITIVE LOGITS
    ischer
    1.36
    aghi
    1.28
     Daniels
    1.21
    8
    1.19
    Json
    1.19
    olius
    1.17
    meri
    1.17
    7
    1.16
    adhi
    1.16
    onen
    1.14
    Act Density 0.269%

    No Known Activations