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

    Neuronpedia

    INDEX
    Explanations

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्यप
    -0.07
    joy
    -0.07
    Browser
    -0.06
    dds
    -0.06
    DownList
    -0.06
    ics
    -0.06
    %-
    -0.06
     وابسته
    -0.06
    -cluster
    -0.06
    bere
    -0.06
    POSITIVE LOGITS
     Baltic
    0.08
     Italians
    0.07
    hetic
    0.07
    AlgorithmException
    0.07
     Scheduled
    0.07
    ceive
    0.06
     SCHOOL
    0.06
     peně
    0.06
     curvature
    0.06
    los
    0.06
    Act Density 0.136%

    No Known Activations