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

    Neuronpedia

    INDEX
    Explanations

    below

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    مار
    -0.07
    bao
    -0.06
    Allocator
    -0.06
    abras
    -0.06
     MessageBoxButton
    -0.06
     Prostit
    -0.06
     몸
    -0.06
    Genres
    -0.06
    endar
    -0.06
     jac
    -0.06
    POSITIVE LOGITS
    "Now
    0.08
    NEXT
    0.07
     unlikely
    0.07
    、ア
    0.06
    اشی
    0.06
     sparing
    0.06
     caucus
    0.06
     caption
    0.06
    .gallery
    0.06
    ceipt
    0.06
    Act Density 0.001%

    No Known Activations