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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     floats
    -0.07
    립
    -0.06
    ionic
    -0.06
    $args
    -0.06
    _dirs
    -0.06
     гід
    -0.06
     Beispiel
    -0.06
    менш
    -0.06
     bahsed
    -0.06
    cki
    -0.06
    POSITIVE LOGITS
     接
    0.07
     Lic
    0.06
    estruct
    0.06
    news
    0.06
    _annotation
    0.06
    ционные
    0.06
     unserialize
    0.06
     initialState
    0.05
     PER
    0.05
    --;↵
    0.05
    Act Density 0.045%

    No Known Activations