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

    Neuronpedia

    INDEX
    Explanations

    top

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يش
    -0.07
     Principles
    -0.06
    Unlike
    -0.06
     Yin
    -0.06
    _guest
    -0.06
     Abel
    -0.06
    dish
    -0.06
    Contains
    -0.06
    ighborhood
    -0.06
    being
    -0.06
    POSITIVE LOGITS
    /win
    0.07
    ázev
    0.07
     scaleY
    0.06
    @email
    0.06
    ประเทศ
    0.06
    -turned
    0.06
     outfield
    0.06
     homosexuality
    0.06
     وهو
    0.06
     day
    0.06
    Act Density 0.011%

    No Known Activations