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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Version
    -0.07
    CUR
    -0.07
    ii
    -0.07
     SEN
    -0.07
    }$/
    -0.06
     toughest
    -0.06
    助
    -0.06
     rou
    -0.06
     Indices
    -0.06
    維
    -0.06
    POSITIVE LOGITS
    手臂
    0.07
    嚓
    0.07
    一樣
    0.07
    原先
    0.07
    سمي
    0.07
     charisma
    0.07
    存在着
    0.07
     사건
    0.07
     هل
    0.07
    _contacts
    0.06
    Act Density 0.048%

    No Known Activations