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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وهذه
    -0.08
     nàng
    -0.07
     kị
    -0.07
    Seeing
    -0.07
     Species
    -0.06
     Canvas
    -0.06
    ITION
    -0.06
     advise
    -0.06
    _BOOK
    -0.06
    곙
    -0.06
    POSITIVE LOGITS
     рассказ
    0.08
     lowest
    0.07
    (center
    0.07
    رض
    0.07
    VP
    0.07
    퍼
    0.07
    //--------------------------------
    0.07
    指责
    0.07
    問題
    0.07
    DD
    0.07
    Act Density 0.071%

    No Known Activations