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

    Neuronpedia

    INDEX
    Explanations

    import pandas as pd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toff
    0.76
    Eff
    0.71
     فور
    0.71
     št
    0.67
    Ako
    0.66
    اتا
    0.65
    Sebagai
    0.65
     شپ
    0.65
    Incorpor
    0.64
    онів
    0.64
    POSITIVE LOGITS
    芎
    0.73
    യിലേ
    0.71
    をご覧ください
    0.71
    urization
    0.70
     destruct
    0.69
     पासवर्ड
    0.69
     Glory
    0.68
    omegal
    0.67
     reused
    0.66
    oucault
    0.66
    Act Density 0.003%

    No Known Activations