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

    Neuronpedia

    INDEX
    Explanations

    virus, lost, in, out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    G
    0.59
     subspaces
    0.53
    C
    0.52
    D
    0.49
     Centre
    0.49
     Bike
    0.49
    ël
    0.47
    ia
    0.47
     amortization
    0.47
    에
    0.46
    POSITIVE LOGITS
    。
    0.57
    秘书
    0.55
     کرده
    0.54
     calda
    0.54
    型
    0.54
    分泌
    0.51
     زمانے
    0.51
    して
    0.50
    する
    0.50
     جاي
    0.50
    Act Density 0.000%

    No Known Activations