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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elena
    -0.07
     арми
    -0.07
     Arbeit
    -0.07
    -use
    -0.07
    anken
    -0.07
    áf
    -0.07
    WSTR
    -0.07
    ा।↵↵
    -0.07
    .quiz
    -0.06
    .css
    -0.06
    POSITIVE LOGITS
     PodsDummy
    0.07
    (keys
    0.07
     оскільки
    0.06
     обычно
    0.06
    γρα
    0.06
     прик
    0.06
     Presented
    0.06
    χο
    0.06
     اروپ
    0.06
    Я
    0.06
    Act Density 0.003%

    No Known Activations