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

    Neuronpedia

    INDEX
    Explanations

    -M

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _nb
    -0.07
     тв
    -0.06
    QR
    -0.06
     Yaz
    -0.06
     hvor
    -0.06
     barbar
    -0.06
    hus
    -0.06
    ाइल
    -0.06
     brut
    -0.06
    .snp
    -0.06
    POSITIVE LOGITS
    ováno
    0.07
    uck
    0.07
     HTTPS
    0.07
     поверхность
    0.07
    -m
    0.07
    mention
    0.07
     madde
    0.06
    _TRANSFER
    0.06
    лива
    0.06
    ès
    0.06
    Act Density 0.000%

    No Known Activations