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

    Neuronpedia

    INDEX
    Explanations

    among

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ROM
    -0.07
     nov
    -0.07
     not
    -0.07
    _tokens
    -0.07
     SPL
    -0.07
    _test
    -0.07
     تبلی
    -0.07
     scar
    -0.07
    Logic
    -0.06
     devastated
    -0.06
    POSITIVE LOGITS
     جمله
    0.06
     Hành
    0.06
    uální
    0.06
    しており
    0.06
     　 　 　
    0.06
    .Pages
    0.06
    PEAT
    0.06
    "struct
    0.06
     Bucks
    0.06
    525
    0.06
    Act Density 0.007%

    No Known Activations