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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incent
    -0.09
    _rating
    -0.09
     constructive
    -0.08
     impetus
    -0.08
    _vec
    -0.08
     إمكانية
    -0.08
    setter
    -0.08
     incentivo
    -0.08
    rating
    -0.08
    怎么样
    -0.08
    POSITIVE LOGITS
     вашей
    0.09
    填写
    0.08
     aquela
    0.08
    You'll
    0.08
    名称
    0.08
    તમ
    0.08
     your
    0.08
     Ihres
    0.08
    .ev
    0.07
     Ihrer
    0.07
    Act Density 0.023%

    No Known Activations