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

    Neuronpedia

    INDEX
    Explanations

    apply to face, leave for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    もっと
    1.02
    OGRAPHY
    0.96
    也许
    0.86
     чемпионаты
    0.83
     ayatan
    0.82
     propried
    0.82
    蔽
    0.82
     fournit
    0.81
     prophes
    0.81
     proprietà
    0.79
    POSITIVE LOGITS
    y
    1.07
    tag
    0.84
    gage
    0.84
     G
    0.81
    ी
    0.80
    dır
    0.80
    ي
    0.80
    tart
    0.79
     N
    0.79
    it
    0.76
    Act Density 0.000%

    No Known Activations