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

    Neuronpedia

    INDEX
    Explanations

    side effects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     华
    -0.07
     etiquette
    -0.07
    Letter
    -0.07
     releasing
    -0.07
    应该
    -0.06
    -talk
    -0.06
     Fred
    -0.06
     查
    -0.06
    folios
    -0.06
    454
    -0.06
    POSITIVE LOGITS
    益
    0.06
    %)
    0.06
    ."));↵
    0.06
    	ROM
    0.06
    .preventDefault
    0.06
    .checkBox
    0.06
    forward
    0.06
    ++;
↵
    0.06
     Imp
    0.06
    φορά
    0.06
    Act Density 0.062%

    No Known Activations