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

    Neuronpedia

    INDEX
    Explanations

    dash Input Output dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dA
    0.60
     ಯಾವುದೇ
    0.55
     decât
    0.54
    cią
    0.52
    kiej
    0.52
    istosoma
    0.52
    dW
    0.51
    FBSDKError
    0.51
     ל
    0.51
     downfall
    0.51
    POSITIVE LOGITS
    巣
    0.55
     carcinogenesis
    0.49
    们
    0.49
    с
    0.48
    opathy
    0.47
    瀑
    0.47
    ව
    0.46
    临床
    0.46
     সীমান্ত
    0.46
     Effekt
    0.45
    Act Density 0.000%

    No Known Activations