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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smokers
    -0.06
     Common
    -0.06
     zcela
    -0.06
    (employee
    -0.06
    finity
    -0.06
    _ack
    -0.06
    ír
    -0.06
     Marcus
    -0.06
     NOT
    -0.06
     ($("#
    -0.06
    POSITIVE LOGITS
    -how
    0.06
    _mode
    0.06
    ley
    0.06
    (#)
    0.06
    やす
    0.06
     แล
    0.06
    (if
    0.06
    _verify
    0.06
    Than
    0.06
     entrusted
    0.06
    Act Density 0.007%

    No Known Activations