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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不幸
    -0.08
    楣
    -0.08
    ADMIN
    -0.07
    もなく
    -0.07
    也是如此
    -0.07
    hel
    -0.07
     darauf
    -0.07
    حدث
    -0.07
    ()];↵
    -0.07
    려
    -0.07
    POSITIVE LOGITS
     автоматы
    0.07
    魏
    0.07
    _sf
    0.07
     gint
    0.07
     means
    0.07
    なんと
    0.07
     blond
    0.07
     Penis
    0.07
    ечен
    0.06
     Glad
    0.06
    Act Density 0.045%

    No Known Activations