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

    Neuronpedia

    INDEX
    Explanations

    software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TestUtils
    -0.07
     ка
    -0.07
    ".$
    -0.06
    _tiles
    -0.06
    _LL
    -0.06
    ンの
    -0.06
     design
    -0.06
     repair
    -0.06
     BaseController
    -0.06
     pricey
    -0.06
    POSITIVE LOGITS
     collo
    0.07
     な
    0.06
    ıda
    0.06
    Except
    0.06
    NL
    0.06
    Unc
    0.06
    :x
    0.06
    ноз
    0.06
    Break
    0.06
     Inspir
    0.06
    Act Density 0.002%

    No Known Activations