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

    Neuronpedia

    INDEX
    Explanations

    card descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opponents
    -0.08
    bens
    -0.07
    	sh
    -0.07
     الدين
    -0.07
    昆仑
    -0.07
    ぼ
    -0.07
     Supplies
    -0.07
    び
    -0.07
     d
    -0.07
    登入
    -0.07
    POSITIVE LOGITS
    翷
    0.08
    윤
    0.07
    ,False
    0.07
    _major
    0.07
     يأتي
    0.07
     (!(
    0.07
     steep
    0.06
    一对
    0.06
     OnTrigger
    0.06
    バイク
    0.06
    Act Density 0.013%

    No Known Activations