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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilor
    -0.07
    ave
    -0.06
    851
    -0.06
    formik
    -0.06
    667
    -0.06
    _urls
    -0.06
    bole
    -0.06
     whereby
    -0.06
    스를
    -0.06
    Clause
    -0.06
    POSITIVE LOGITS
     MF
    0.07
    作品
    0.07
    .Formatting
    0.07
    CELER
    0.06
     adventurer
    0.06
    Lim
    0.06
     Kostenlos
    0.06
     Feder
    0.06
     OCC
    0.06
     filmer
    0.06
    Act Density 0.231%

    No Known Activations