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

    Neuronpedia

    INDEX
    Explanations

    key performance indicators

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dance
    -0.09
    _safe
    -0.07
    Refresh
    -0.07
    .save
    -0.07
     ua
    -0.07
    
    -0.07
     escaping
    -0.07
    Challenge
    -0.06
    "display
    -0.06
    leck
    -0.06
    POSITIVE LOGITS
     中国
    0.07
     سل
    0.07
     отверсти
    0.07
     Mus
    0.06
    rgyz
    0.06
     приготовить
    0.06
    六
    0.06
    /g
    0.06
    Got
    0.06
    reme
    0.06
    Act Density 0.081%

    No Known Activations