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

    Neuronpedia

    INDEX
    Explanations

    code and identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Thread
    -0.06
     металли
    -0.06
    );↵
    -0.06
     chaud
    -0.06
    roupe
    -0.06
    رج
    -0.06
    quirrel
    -0.06
    urrets
    -0.06
     proximity
    -0.06
     рах
    -0.06
    POSITIVE LOGITS
     Kansas
    0.06
     impass
    0.06
     Spoj
    0.06
     genuinely
    0.06
    (model
    0.06
    _widgets
    0.06
    ilmiştir
    0.06
    oval
    0.06
     diseñ
    0.06
     Houston
    0.06
    Act Density 0.060%

    No Known Activations