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

    Neuronpedia

    INDEX
    Explanations

    playlist curators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मू
    0.44
     screws
    0.44
    ଛ
    0.44
     fittings
    0.42
     controlling
    0.42
     ک
    0.41
     பொருட்கள்
    0.41
     ''.
    0.41
     fortifications
    0.40
     diathermy
    0.40
    POSITIVE LOGITS
    一张
    0.50
    rée
    0.49
    т
    0.47
    }:
    0.47
    ,
    0.43
     veya
    0.43
    忥
    0.43
     yeni
    0.42
    和社会
    0.42
    全新
    0.42
    Act Density 0.005%

    No Known Activations