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

    Neuronpedia

    INDEX
    Explanations

    teeth variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.04
    ﺪ
    1.04
    िंग
    1.02
    ﮐ
    1.00
    er
    0.97
    の値
    0.96
    ка
    0.96
    کم
    0.95
    점에서
    0.92
    ク
    0.89
    POSITIVE LOGITS
     tooth
    1.19
     Tooth
    1.18
     teeth
    1.13
    牙
    1.13
     Teeth
    0.99
    你
    0.92
     an
    0.89
    '
    0.87
    ering
    0.84
    齿
    0.83
    Act Density 0.004%

    No Known Activations