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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blow
    -0.06
     --------
    -0.06
     libr
    -0.06
    ‌هایی
    -0.06
    _cores
    -0.06
    Matches
    -0.06
    <H
    -0.06
    (!
    -0.06
     `-
    -0.06
    —who
    -0.06
    POSITIVE LOGITS
    こと
    0.06
    werk
    0.06
    forder
    0.06
    Ｄ
    0.06
    aiser
    0.06
    Redux
    0.06
    bdd
    0.06
    raci
    0.06
    جان
    0.06
    时代
    0.06
    Act Density 0.002%

    No Known Activations