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

    Neuronpedia

    INDEX
    Explanations

    disable, enable, lock, table

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tann
    0.43
     prestación
    0.42
    ნი
    0.41
     séparation
    0.40
     hậu
    0.39
     zar
    0.38
    མ་
    0.38
    льную
    0.38
    дени
    0.38
    ồi
    0.38
    POSITIVE LOGITS
    Disable
    0.76
     disable
    0.68
     disabled
    0.67
    Disabled
    0.67
    disable
    0.66
     disabling
    0.64
     disables
    0.63
     Disable
    0.63
    disabled
    0.60
     Disabled
    0.59
    Act Density 0.002%

    No Known Activations