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

    Neuronpedia

    INDEX
    Explanations

    pseudo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifa
    -0.07
    حكومة
    -0.07
     bill
    -0.07
    unidad
    -0.06
    עונה
    -0.06
     tí
    -0.06
     juices
    -0.06
    صيب
    -0.06
     alerts
    -0.06
    Stroke
    -0.06
    POSITIVE LOGITS
     Alto
    0.08
    燚
    0.07
    ダイエ
    0.07
     makers
    0.07
    鲂
    0.07
    .variant
    0.07
    interopRequire
    0.07
     Хот
    0.06
    _PRED
    0.06
    飘
    0.06
    Act Density 0.003%

    No Known Activations