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

    Neuronpedia

    INDEX
    Explanations

    system descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zou
    -0.07
     dette
    -0.07
     }])↵
    -0.07
    了我的
    -0.07
     panties
    -0.06
    .She
    -0.06
     coatings
    -0.06
    .visible
    -0.06
    (Box
    -0.06
    >((
    -0.06
    POSITIVE LOGITS
     Pep
    0.07
     Trans
    0.07
    ации
    0.07
    Classifier
    0.07
    cles
    0.07
     UCS
    0.07
     unprotected
    0.07
    [data
    0.06
    _enter
    0.06
     Only
    0.06
    Act Density 0.313%

    No Known Activations