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

    Neuronpedia

    INDEX
    Explanations

    academic/research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Queue
    -0.07
    Illuminate
    -0.07
    Fal
    -0.06
     Erotische
    -0.06
    BuilderFactory
    -0.06
     setSupportActionBar
    -0.06
     abbreviated
    -0.06
     supposedly
    -0.06
    Localized
    -0.06
     yardımcı
    -0.06
    POSITIVE LOGITS
     -↵
    0.07
     corporations
    0.07
     —↵
    0.07
     bosses
    0.07
     corporation
    0.06
     اگر
    0.06
    NEXT
    0.06
    REF
    0.06
    -
↵
    0.06
     jog
    0.06
    Act Density 0.003%

    No Known Activations