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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rections
    -0.07
    _salt
    -0.07
     Shak
    -0.07
    ustomer
    -0.07
    urity
    -0.07
     magnesium
    -0.07
    沙
    -0.07
    MAIL
    -0.07
     بق
    -0.07
     Butt
    -0.06
    POSITIVE LOGITS
     Object
    0.06
    (KeyEvent
    0.06
     INFORMATION
    0.06
    JSONException
    0.06
    Heroes
    0.06
    走
    0.06
    _REQUIRED
    0.06
    Canceled
    0.06
     tức
    0.06
    ymbol
    0.06
    Act Density 0.001%

    No Known Activations