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

    Neuronpedia

    INDEX
    Explanations

    clothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ס
    1.00
     are
    0.95
    ב
    0.86
     gustaría
    0.81
    ה
    0.80
     società
    0.79
     conosc
    0.78
    CM
    0.78
     отношения
    0.78
     sonuç
    0.77
    POSITIVE LOGITS
    ments
    1.02
    ir
    0.95
    iation
    0.93
    assapi
    0.93
    jot
    0.90
    ppard
    0.83
     Clothes
    0.82
     insulators
    0.81
    ahuasca
    0.81
    clothes
    0.80
    Act Density 0.013%

    No Known Activations