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

    Neuronpedia

    INDEX
    Explanations

    contemptuous questions and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可能
    1.13
     möglicherweise
    1.07
     немного
    1.07
    较为
    1.05
     可能
    1.03
     😊
    1.03
    😊
    1.02
     возможно
    1.01
    可能会
    1.01
     önemlidir
    1.01
    POSITIVE LOGITS
     ridiculous
    2.48
     ludicrous
    2.46
     absurd
    2.27
     pathetic
    2.20
     laughable
    2.12
     absurdity
    2.09
     stupid
    2.02
     disgusting
    1.97
     stupidity
    1.94
     bullshit
    1.93
    Act Density 0.452%

    No Known Activations