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

    Neuronpedia

    INDEX
    Explanations

    coding operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     komunik
    -0.08
     stained
    -0.08
     touchdowns
    -0.08
    hões
    -0.08
     Communication
    -0.07
     fires
    -0.07
     témo
    -0.07
    -painted
    -0.07
     교
    -0.07
    .confirm
    -0.07
    POSITIVE LOGITS
     unary
    0.17
     Unary
    0.16
    Unary
    0.15
     अके
    0.09
     converting
    0.09
     sola
    0.09
     convierte
    0.09
     standalone
    0.09
     conversion
    0.09
    REFIX
    0.09
    Act Density 0.014%

    No Known Activations