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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vias
    -0.08
     فروش
    -0.08
     Aktien
    -0.07
    尿
    -0.07
    urances
    -0.07
    odian
    -0.07
     potr
    -0.07
    ahin
    -0.07
     Wilmington
    -0.07
     해서
    -0.07
    POSITIVE LOGITS
    /question
    0.09
     imaginable
    0.09
    /projects
    0.09
    /data
    0.08
    /course
    0.08
     поступ
    0.08
     aparentemente
    0.08
    /news
    0.08
     apresentada
    0.08
     undertaken
    0.08
    Act Density 0.162%

    No Known Activations