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

    Neuronpedia

    INDEX
    Explanations

    CSPM, recognizing risks, recall check, Allah accept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    op
    0.48
    lak
    0.46
    abel
    0.45
    q
    0.45
    ds
    0.44
    č
    0.44
    ck
    0.44
    લ
    0.44
    ),
    0.43
    k
    0.42
    POSITIVE LOGITS
     റേ
    0.49
    मूलन
    0.49
     وقوع
    0.49
    MOUNTAINS
    0.47
    ায়ণ
    0.47
     ரே
    0.47
    ExposureTime
    0.45
    гона
    0.45
    IDENCE
    0.44
     IAU
    0.44
    Act Density 0.001%

    No Known Activations