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

    Neuronpedia

    INDEX
    Explanations

    please

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dou
    -0.07
    Scala
    -0.07
    胎
    -0.06
     bí
    -0.06
     kì
    -0.06
     Pai
    -0.06
    ाण
    -0.06
     Distrib
    -0.06
     قائمة
    -0.06
    Dou
    -0.06
    POSITIVE LOGITS
    ует
    0.07
     Plenty
    0.07
    (raw
    0.07
     restarting
    0.06
     below
    0.06
     >>
    0.06
     떠
    0.06
    ilog
    0.06
    _TAGS
    0.06
     Χα
    0.06
    Act Density 0.023%

    No Known Activations