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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     primitive
    -0.07
    ,"%
    -0.06
     steals
    -0.06
    980
    -0.06
     thang
    -0.06
    .clientHeight
    -0.06
    둥
    -0.06
    uo
    -0.06
    endl
    -0.06
     ولا
    -0.06
    POSITIVE LOGITS
    幸
    0.07
    (cursor
    0.06
    ought
    0.06
     review
    0.06
     Review
    0.06
    /graph
    0.06
     yaml
    0.06
     prompted
    0.06
     togg
    0.06
     forever
    0.06
    Act Density 0.030%

    No Known Activations