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

    Neuronpedia

    INDEX
    Explanations

    division in sampling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     закон
    -0.08
    dock
    -0.08
     Babel
    -0.08
     unaffected
    -0.08
     забы
    -0.08
     protoc
    -0.08
    atories
    -0.07
     xmlns
    -0.07
     aerospace
    -0.07
     clay
    -0.07
    POSITIVE LOGITS
     periode
    0.09
    periode
    0.08
    ipay
    0.08
    approx
    0.08
     approximate
    0.08
    elig
    0.08
    ratio
    0.08
    _ratio
    0.07
     daje
    0.07
    _RATIO
    0.07
    Act Density 0.009%

    No Known Activations