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

    Neuronpedia

    INDEX
    Explanations

    Writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     virus
    -0.07
     Без
    -0.07
    components
    -0.07
    infos
    -0.06
    他的
    -0.06
    шие
    -0.06
    day
    -0.06
     dictated
    -0.06
    indre
    -0.06
     NPCs
    -0.06
    POSITIVE LOGITS
     fakt
    0.08
    Apple
    0.07
     module
    0.07
     Bollywood
    0.06
    -------------</
    0.06
    _pll
    0.06
     Elekt
    0.06
    (expected
    0.06
    .ml
    0.06
     officially
    0.06
    Act Density 0.002%

    No Known Activations