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

    Neuronpedia

    INDEX
    Explanations

    absurdity and humor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     νε
    -0.09
     суще
    -0.08
     сформ
    -0.08
    .Н
    -0.08
    kani
    -0.08
     പല
    -0.08
    ,we
    -0.08
     данной
    -0.08
    .Т
    -0.08
     формирования
    -0.08
    POSITIVE LOGITS
     hilarious
    0.15
     bizarre
    0.15
     😂
    0.14
     absurd
    0.14
     ridiculously
    0.14
     antics
    0.13
     quirky
    0.13
     amusing
    0.13
     jokes
    0.12
     ridiculous
    0.12
    Act Density 1.350%

    No Known Activations