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

    Neuronpedia

    INDEX
    Explanations

    un

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embarrassment
    -0.07
    typings
    -0.06
    Explorer
    -0.06
     Providers
    -0.06
    ISE
    -0.06
     differs
    -0.06
     Overlay
    -0.06
     Soap
    -0.06
     births
    -0.06
     expressly
    -0.06
    POSITIVE LOGITS
    skin
    0.07
     😉↵↵
    0.06
     Psalm
    0.06
    ندگان
    0.06
    бут
    0.06
     uluslararası
    0.06
     unn
    0.06
    ऊ
    0.06
    lyn
    0.06
     시즌
    0.06
    Act Density 0.002%

    No Known Activations