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

    Neuronpedia

    INDEX
    Explanations

    R code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Suites
    -0.07
    ())↵↵
    -0.07
    -platform
    -0.07
    ]='\
    -0.07
    vector
    -0.07
     receiving
    -0.06
     :-)
    -0.06
    [])
↵
    -0.06
    _noise
    -0.06
    ?>↵↵
    -0.06
    POSITIVE LOGITS
    iek
    0.07
    уру
    0.06
     pag
    0.06
     Δεν
    0.06
     выдел
    0.06
     karşı
    0.06
     lleg
    0.06
     getir
    0.06
     Zheng
    0.06
     Petr
    0.06
    Act Density 0.009%

    No Known Activations