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

    Neuronpedia

    INDEX
    Explanations

    Artificial intelligence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -bed
    -0.07
     дод
    -0.06
    _perm
    -0.06
     Marines
    -0.06
    Kit
    -0.06
    TEM
    -0.06
    -notch
    -0.06
     Khu
    -0.06
    /app
    -0.06
    Ingredient
    -0.06
    POSITIVE LOGITS
     свобод
    0.07
     painted
    0.06
     bracket
    0.06
    نسان
    0.06
     furnace
    0.06
    running
    0.06
    ,$_
    0.06
     Railroad
    0.06
    _________________↵↵
    0.06
     Twins
    0.06
    Act Density 0.010%

    No Known Activations