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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tele
    -0.08
     typeof
    -0.07
     Rex
    -0.06
     EntityState
    -0.06
    :',↵
    -0.06
    ADX
    -0.06
     与
    -0.06
    _ssl
    -0.06
    yla
    -0.06
     Var
    -0.06
    POSITIVE LOGITS
    oleč
    0.07
    .sound
    0.06
    {{--
    0.06
    ุคคล
    0.06
    _CASE
    0.05
    jící
    0.05
     мой
    0.05
    πο
    0.05
    ************************
    0.05
     Argument
    0.05
    Act Density 0.488%

    No Known Activations