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

    Neuronpedia

    INDEX
    Explanations

    seat of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    기
    1.16
    ために
    1.11
    ки
    1.10
    MIS
    1.09
    PER
    0.98
     manchas
    0.96
     мастеров
    0.95
     células
    0.94
    Singleton
    0.92
    Sistema
    0.92
    POSITIVE LOGITS
    u
    1.82
    p
    1.34
     (
    1.24
    ha
    1.24
    ه
    1.21
    ron
    1.09
     by
    1.05
    arı
    1.05
    р
    1.05
     a
    1.04
    Act Density 0.000%

    No Known Activations