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

    Neuronpedia

    INDEX
    Explanations

    legal errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    　ｌ
    -0.07
     notation
    -0.06
     яс
    -0.06
    )::
    -0.06
     trash
    -0.06
    ebo
    -0.06
    olicitud
    -0.06
    _intersection
    -0.06
     默认
    -0.06
     incel
    -0.06
    POSITIVE LOGITS
     آزم
    0.06
     highly
    0.06
     Milano
    0.06
    UNKNOWN
    0.06
    (Long
    0.06
    .Windows
    0.06
    _OPTIONS
    0.06
     Leia
    0.06
    _STYLE
    0.06
     літ
    0.06
    Act Density 0.003%

    No Known Activations