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

    Neuronpedia

    INDEX
    Explanations

    Symbols and the letter "I"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dort
    -0.07
    弄
    -0.07
    tvrt
    -0.06
     нанес
    -0.06
    -même
    -0.06
    urtle
    -0.06
    -inverse
    -0.06
    ACS
    -0.06
     zákona
    -0.06
     tamb
    -0.06
    POSITIVE LOGITS
    hydrate
    0.06
    aptured
    0.06
    _WEAPON
    0.06
     scrolled
    0.06
    incre
    0.06
     Mant
    0.06
    sexual
    0.06
    downloads
    0.06
    _fit
    0.06
    ussen
    0.06
    Act Density 0.006%

    No Known Activations