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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рай
    -0.07
    idi
    -0.06
    adge
    -0.06
    afd
    -0.06
    ack
    -0.06
    دید
    -0.06
    di
    -0.06
     interpreting
    -0.06
     усл
    -0.06
    ToStr
    -0.06
    POSITIVE LOGITS
    tember
    0.07
     Needless
    0.07
     ін
    0.07
     LogLevel
    0.06
    ragment
    0.06
    illation
    0.06
    ;")↵
    0.06
     skeletons
    0.06
     outro
    0.06
    材
    0.06
    Act Density 0.202%

    No Known Activations