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

    Neuronpedia

    INDEX
    Explanations

    Parse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abandonment
    -0.07
    .";↵↵
    -0.07
    )))↵↵↵
    -0.06
     Bard
    -0.06
    BL
    -0.06
    ))))↵↵
    -0.06
    Either
    -0.06
    ีบ
    -0.06
    Maintenance
    -0.06
     ए
    -0.06
    POSITIVE LOGITS
     fuzz
    0.07
    .optim
    0.07
    .MaximizeBox
    0.07
    ItemSelected
    0.07
     Read
    0.06
    _predict
    0.06
     eerste
    0.06
    .Com
    0.06
    (loc
    0.06
     Yorkers
    0.06
    Act Density 0.002%

    No Known Activations