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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    狗
    -0.07
    (dateTime
    -0.06
     디
    -0.06
     تلف
    -0.06
     cof
    -0.06
     无
    -0.06
     Discovery
    -0.06
     INTERVAL
    -0.06
    企业
    -0.06
    bservable
    -0.06
    POSITIVE LOGITS
    (END
    0.07
     Král
    0.07
    wik
    0.06
    çesi
    0.06
    тар
    0.06
    emax
    0.06
    녕
    0.06
    ecurity
    0.06
    clc
    0.06
    -value
    0.06
    Act Density 0.040%

    No Known Activations