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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /ap
    -0.06
    _ap
    -0.06
    $max
    -0.06
    .Unique
    -0.06
    	the
    -0.06
     silly
    -0.06
     keine
    -0.06
    fortawesome
    -0.06
     결과
    -0.06
    ifications
    -0.06
    POSITIVE LOGITS
     důvodu
    0.07
     навч
    0.06
     )}↵
    0.06
    DbType
    0.06
     }}">↵
    0.06
    byss
    0.06
    addon
    0.06
    -native
    0.06
     kısm
    0.06
     sociální
    0.06
    Act Density 0.024%

    No Known Activations