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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     putchar
    -0.07
     Cumberland
    -0.07
    altern
    -0.06
     FR
    -0.06
     III
    -0.06
     consoles
    -0.06
    HB
    -0.06
     noci
    -0.06
    CellStyle
    -0.06
    mae
    -0.06
    POSITIVE LOGITS
    (vertical
    0.07
    래스
    0.07
     определить
    0.06
     innovations
    0.06
     barely
    0.06
     skateboard
    0.06
    하세요
    0.06
    elan
    0.06
     تلفن
    0.06
     guideline
    0.06
    Act Density 0.003%

    No Known Activations