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

    Neuronpedia

    INDEX
    Explanations

    Dates and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arası
    -0.07
     존재
    -0.07
    Lexer
    -0.06
    .randint
    -0.06
    _credit
    -0.06
     Wrapper
    -0.06
    _DR
    -0.06
     gele
    -0.06
    senha
    -0.06
    ／
    -0.06
    POSITIVE LOGITS
     akşam
    0.07
    ."),↵
    0.07
     disclosing
    0.06
    APON
    0.06
    Brain
    0.06
     firms
    0.06
    637
    0.06
     示
    0.06
     happy
    0.06
    RT
    0.06
    Act Density 0.000%

    No Known Activations