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

    Neuronpedia

    INDEX
    Explanations

    initialization or definition setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    서
    2.63
    ছেন
    2.25
    いた
    2.03
     handcuffs
    2.03
     Offences
    1.95
    ことも
    1.94
     않은
    1.90
    शेखर
    1.90
    да
    1.88
     Tregs
    1.84
    POSITIVE LOGITS
    و
    2.84
    tive
    2.31
    TimeSeries
    2.25
    Type
    2.23
    Text
    2.19
    tions
    2.19
    tart
    2.19
    ین
    2.14
    kka
    2.14
    larda
    2.13
    Act Density 0.113%

    No Known Activations