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

    Neuronpedia

    INDEX
    Explanations

    code/URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enfants
    -0.07
    áz
    -0.07
     Bris
    -0.06
     Theatre
    -0.06
     Alban
    -0.06
     túi
    -0.06
     Improved
    -0.06
     fors
    -0.06
     вес
    -0.06
     Applies
    -0.06
    POSITIVE LOGITS
     Yıl
    0.08
    ونی
    0.07
    CODE
    0.07
     orgasm
    0.06
                                ↵
    0.06
     screamed
    0.06
     erotica
    0.06
    roduction
    0.06
     onHide
    0.06
    Multiply
    0.06
    Act Density 0.704%

    No Known Activations