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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expectations
    -0.07
    "&
    -0.07
    年代
    -0.07
    (lon
    -0.06
     Lag
    -0.06
     технолог
    -0.06
     Hello
    -0.06
     rape
    -0.06
    -session
    -0.06
     Performing
    -0.06
    POSITIVE LOGITS
     //}↵
    0.06
     unbiased
    0.06
    fox
    0.06
     �
    0.06
     крок
    0.06
     เพราะ
    0.06
     patt
    0.06
    _identifier
    0.06
    .comp
    0.06
     breadcrumb
    0.05
    Act Density 0.030%

    No Known Activations