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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poj
    -0.07
     SPA
    -0.07
    스타
    -0.06
     rhs
    -0.06
    Snow
    -0.06
    .Css
    -0.06
     сви
    -0.06
     curves
    -0.06
     EST
    -0.06
     decoding
    -0.06
    POSITIVE LOGITS
    ЎыџN
    0.07
    _dn
    0.06
    _RANGE
    0.06
    丝
    0.06
     polyline
    0.06
     simmer
    0.06
    اضی
    0.06
    rschein
    0.06
    ื
    0.06
    ），
    0.06
    Act Density 0.153%

    No Known Activations