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

    Neuronpedia

    INDEX
    Explanations

    efficacy against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ہتھی
    0.55
    ociaż
    0.51
     pédicule
    0.49
     amulet
    0.48
     }^{*}$
    0.47
     sitten
    0.47
     aching
    0.47
     Když
    0.47
    洖
    0.47
     ہاتھوں
    0.46
    POSITIVE LOGITS
     operating
    0.46
     Damp
    0.45
    ’
    0.43
    au
    0.42
    ية
    0.42
    urre
    0.42
     up
    0.41
     activation
    0.41
     activated
    0.40
     dampened
    0.40
    Act Density 0.000%

    No Known Activations