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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fuerte
    -0.08
    .None
    -0.08
     мат
    -0.07
     gat
    -0.07
     tuy
    -0.07
    .Ext
    -0.07
     sey
    -0.07
     upbringing
    -0.07
     Eb
    -0.07
    పై
    -0.07
    POSITIVE LOGITS
    ================
    0.08
     ----------------
    0.08
    -------------
    0.08
    -----------
    0.08
    ાણ
    0.08
     --------
    0.08
    ==========
    0.07
    -------
    0.07
    ************************
    0.07
    ------
    0.07
    Act Density 0.002%

    No Known Activations