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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    改
    -0.07
     Nes
    -0.07
     entr
    -0.07
     Ven
    -0.06
     Fleming
    -0.06
    licted
    -0.06
     důsled
    -0.06
     Cin
    -0.06
    _BINDING
    -0.06
    Submission
    -0.06
    POSITIVE LOGITS
    レ
    0.07
     порядку
    0.06
    esser
    0.06
    produ
    0.06
    -at
    0.06
    ектор
    0.06
     проч
    0.06
    -ни
    0.06
    Class
    0.06
    /configuration
    0.06
    Act Density 0.032%

    No Known Activations