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

    Neuronpedia

    INDEX
    Explanations

    possibility or uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ten
    -0.09
    ólicas
    -0.08
    ాండ్
    -0.08
     Fif
    -0.08
    ánd
    -0.08
     функциони
    -0.08
     dë
    -0.08
     trou
    -0.08
    зар
    -0.08
     Herm
    -0.08
    POSITIVE LOGITS
     erwartet
    0.10
     expects
    0.09
     require
    0.08
     refer
    0.08
     calculators
    0.08
     phr
    0.08
     emphasize
    0.08
    作文
    0.07
     textbooks
    0.07
     expecting
    0.07
    Act Density 0.077%

    No Known Activations