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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Termin
    -0.07
     популяр
    -0.07
     yên
    -0.07
    (prod
    -0.06
    泳
    -0.06
    _packages
    -0.06
    _registro
    -0.06
    _SENS
    -0.06
     melan
    -0.06
    piler
    -0.06
    POSITIVE LOGITS
    直接
    0.07
     HelloWorld
    0.07
    宗
    0.06
    krvldkf
    0.06
     Adler
    0.06
     fluctuations
    0.06
     autor
    0.06
     🙂
    0.06
     Enrique
    0.06
     excluded
    0.06
    Act Density 0.026%

    No Known Activations