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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Emmanuel
    -0.07
     surrendered
    -0.06
     unconscious
    -0.06
    HW
    -0.06
    803
    -0.06
     Selenium
    -0.06
    cult
    -0.06
    relu
    -0.06
     ฉ
    -0.06
     Stevens
    -0.06
    POSITIVE LOGITS
    :!
    0.07
    {!!
    0.07
    。↵↵↵↵
    0.07
    ное
    0.07
    !!
    0.07
    ных
    0.06
    ?!↵↵
    0.06
    __)↵↵↵
    0.06
    枚
    0.06
    ・
    0.06
    Act Density 0.008%

    No Known Activations