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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WHY
    -0.06
    出す
    -0.06
    Slash
    -0.06
    _STRIP
    -0.06
     only
    -0.06
    nothing
    -0.06
    /B
    -0.06
    Fully
    -0.06
    Năm
    -0.06
     Nobody
    -0.06
    POSITIVE LOGITS
     boto
    0.07
    워크
    0.07
     совет
    0.07
     حاج
    0.07
    igen
    0.07
    ilda
    0.07
     teknik
    0.07
     офици
    0.06
    IXEL
    0.06
    _TEM
    0.06
    Act Density 0.049%

    No Known Activations