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

    Neuronpedia

    INDEX
    Explanations

    variable/index names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    browse
    -0.07
     commencement
    -0.06
    (program
    -0.06
    步行
    -0.06
    +"/"+
    -0.06
    BUTTON
    -0.06
     cite
    -0.06
    텉
    -0.06
    ]='
    -0.06
    ...");
↵
    -0.06
    POSITIVE LOGITS
    $i
    0.08
    Iterator
    0.08
     khuẩn
    0.08
    -quarter
    0.07
    acs
    0.07
    酬
    0.07
    lık
    0.07
     الفكر
    0.07
     Vendor
    0.07
     też
    0.07
    Act Density 0.029%

    No Known Activations