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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    waż
    -0.07
     Aer
    -0.07
     Hungary
    -0.07
     EVAL
    -0.07
    mini
    -0.06
     snprintf
    -0.06
    重复
    -0.06
    肚子
    -0.06
     Yönetim
    -0.06
    ]int
    -0.06
    POSITIVE LOGITS
    ת
    0.08
    ظ
    0.07
    亲人
    0.07
    ведите
    0.07
    クロ
    0.07
    Fox
    0.06
     normals
    0.06
     Accessibility
    0.06
    큻
    0.06
     '.
    0.06
    Act Density 0.004%

    No Known Activations