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

    Neuronpedia

    INDEX
    Explanations

    hotel amenities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.51
    ing
    1.19
     I
    1.06
    ۔
    1.05
    h
    1.02
    yl
    0.88
     Medical
    0.87
    ب
    0.86
     Muay
    0.85
    op
    0.85
    POSITIVE LOGITS
     amenities
    1.24
    ع
    1.05
     своё
    1.02
    ו
    0.99
    чита
    0.98
    ר
    0.96
    ي
    0.96
    де
    0.93
     рассказыва
    0.92
     complet
    0.91
    Act Density 0.001%

    No Known Activations