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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    깣
    -0.07
    Jun
    -0.07
    ificance
    -0.07
    enze
    -0.07
    ical
    -0.06
    ТИ
    -0.06
    meta
    -0.06
     visibility
    -0.06
    新西兰
    -0.06
    희
    -0.06
    POSITIVE LOGITS
    כנים
    0.07
    :C
    0.07
     pracownik
    0.07
    +b
    0.07
    (comb
    0.07
    _acl
    0.07
    cona
    0.07
    _floor
    0.07
    绹
    0.07
     PP
    0.07
    Act Density 0.143%

    No Known Activations