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

    Neuronpedia

    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arguably
    -0.08
    Black
    -0.08
    زاد
    -0.07
     EJ
    -0.07
     Black
    -0.07
     PJ
    -0.07
     MJ
    -0.07
    ブラック
    -0.07
     exception
    -0.07
    عديد
    -0.07
    POSITIVE LOGITS
     licking
    0.08
     использование
    0.08
     듣
    0.08
    .aliy
    0.08
     необходимость
    0.07
     ше
    0.07
     конец
    0.07
     создание
    0.07
     состояние
    0.07
     thirst
    0.07
    Act Density 0.000%

    No Known Activations