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

    Neuronpedia

    INDEX
    Explanations

    demon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scarce
    -0.07
    こんにちは
    -0.07
     somew
    -0.07
    жив
    -0.07
     Crest
    -0.07
     windy
    -0.07
    ipp
    -0.07
     jeu
    -0.07
     tsl
    -0.07
     deği
    -0.07
    POSITIVE LOGITS
     signals
    0.07
     demon
    0.07
    EMALE
    0.07
     symbols
    0.07
    -description
    0.07
    ⬡
    0.07
    'an
    0.07
    |↵
    0.07
    alar
    0.06
    _PRODUCT
    0.06
    Act Density 0.003%

    No Known Activations