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

    Neuronpedia

    INDEX
    Explanations

    Rem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nero
    -0.09
     Ryan
    -0.09
    歡
    -0.08
    ă
    -0.08
    धान
    -0.08
    _nt
    -0.08
     Bonus
    -0.08
     ópt
    -0.08
    ært
    -0.08
     周
    -0.08
    POSITIVE LOGITS
    pl
    0.13
    Pl
    0.09
     pl
    0.09
    PL
    0.09
    (pl
    0.09
    pli
    0.08
    snow
    0.08
    大厅
    0.08
    Pig
    0.08
    	pl
    0.08
    Act Density 0.000%

    No Known Activations