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

    Neuronpedia

    INDEX
    Explanations

    base64 decoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eresis
    0.78
    ๘
    0.74
     Abub
    0.74
    ipolar
    0.68
    loed
    0.68
    uild
    0.68
     گراف
    0.67
    нную
    0.67
     repos
    0.67
    gotoxy
    0.67
    POSITIVE LOGITS
    Mj
    1.12
    MT
    1.02
    NDE
    0.99
    MDA
    0.94
    Nj
    0.94
    Zm
    0.94
    Ij
    0.91
    Nz
    0.90
    Mz
    0.90
    ZW
    0.89
    Act Density 0.042%

    No Known Activations