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

    Neuronpedia

    INDEX
    Explanations

    far

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     annually
    -0.09
     obtainable
    -0.08
     rédu
    -0.08
     Publ
    -0.08
    _PRINTF
    -0.07
     commuter
    -0.07
    univers
    -0.07
     CHF
    -0.07
     Furthermore
    -0.07
    š
    -0.07
    POSITIVE LOGITS
     बातचीत
    0.10
     asking
    0.09
     previous
    0.09
     conversar
    0.09
    回应
    0.08
     conversation
    0.08
    .ask
    0.08
     Gespräch
    0.08
     Bow
    0.08
     Assistant
    0.08
    Act Density 0.027%

    No Known Activations