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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    웻
    -0.07
    VOID
    -0.07
    .Nil
    -0.07
    beschäft
    -0.07
    	atomic
    -0.06
    ritos
    -0.06
     mailed
    -0.06
    StringUtils
    -0.06
    镵
    -0.06
     WRITE
    -0.06
    POSITIVE LOGITS
    pps
    0.08
     deviations
    0.07
     einfach
    0.07
    淡淡的
    0.07
    Rod
    0.07
     역시
    0.07
    ”)
    0.07
     inclusion
    0.07
    把他
    0.07
     Alexander
    0.07
    Act Density 0.008%

    No Known Activations