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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    火
    -0.07
     sint
    -0.07
    References
    -0.06
    cards
    -0.06
     Pages
    -0.06
    손
    -0.06
    -described
    -0.06
    bbing
    -0.06
    (cls
    -0.06
     harms
    -0.06
    POSITIVE LOGITS
     QLabel
    0.08
     England
    0.06
    kový
    0.06
    ле
    0.06
     flask
    0.06
    ingen
    0.06
    inn
    0.06
     suite
    0.06
    _supplier
    0.06
    .tableView
    0.06
    Act Density 0.025%

    No Known Activations