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

    Neuronpedia

    INDEX
    Explanations

    Errors and misleading results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    訴
    -0.07
     Ply
    -0.07
     aute
    -0.07
     academics
    -0.07
     breast
    -0.07
    @↵↵
    -0.06
    プロ
    -0.06
    .White
    -0.06
    .AC
    -0.06
    .Persistence
    -0.06
    POSITIVE LOGITS
    开采
    0.08
    food
    0.07
    CanBeConverted
    0.07
    ѝ
    0.07
    וידאו
    0.07
    gerät
    0.07
    stdcall
    0.06
    冽
    0.06
     dirs
    0.06
    _GF
    0.06
    Act Density 0.123%

    No Known Activations