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

    Neuronpedia

    INDEX
    Explanations

    references to other sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isku
    -0.08
     Teams
    -0.07
    blink
    -0.06
    (cart
    -0.06
    (menu
    -0.06
     Swim
    -0.06
     đau
    -0.06
    Preferences
    -0.06
     citrus
    -0.06
     swore
    -0.06
    POSITIVE LOGITS
    UNC
    0.06
    콜걸
    0.06
     کوچ
    0.06
     ----------↵
    0.06
    ImageSharp
    0.06
     unfairly
    0.06
     odpowied
    0.06
    ตร
    0.06
    caffold
    0.06
     fif
    0.06
    Act Density 0.019%

    No Known Activations