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

    Neuronpedia

    INDEX
    Explanations

    general English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fend
    -0.06
    ('*',
    -0.06
    _schema
    -0.06
     väl
    -0.06
    ζη
    -0.06
    .Play
    -0.06
    :name
    -0.06
     кур
    -0.06
    .writer
    -0.06
     lety
    -0.06
    POSITIVE LOGITS
    ন
    0.07
     Bip
    0.07
     tay
    0.06
    November
    0.06
    MS
    0.06
    盘
    0.06
     BACK
    0.06
    ować
    0.06
    lığ
    0.06
    reta
    0.06
    Act Density 0.000%

    No Known Activations