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

    Neuronpedia

    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Table
    -0.07
     mdi
    -0.06
     inse
    -0.06
    扱
    -0.06
     Sele
    -0.06
    Date
    -0.06
    ucene
    -0.06
     Literal
    -0.06
     впол
    -0.06
    Mis
    -0.06
    POSITIVE LOGITS
    (False
    0.07
    udes
    0.07
     pomocí
    0.07
     inaug
    0.06
    (cfg
    0.06
     aVar
    0.06
    _iv
    0.06
    ültür
    0.06
     SIMPLE
    0.06
    yx
    0.06
    Act Density 0.000%

    No Known Activations