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

    Neuronpedia

    INDEX
    Explanations

    Names, numbers, or videos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _radius
    -0.08
    易
    -0.07
    :|
    -0.07
     مرة
    -0.07
    收入
    -0.07
     kiss
    -0.06
     payout
    -0.06
    Classes
    -0.06
     lat
    -0.06
    _Selected
    -0.06
    POSITIVE LOGITS
    isson
    0.06
    /base
    0.06
    ­
    0.06
    ogle
    0.06
    kj
    0.06
     abst
    0.06
     Sioux
    0.06
    보고
    0.06
     bile
    0.06
     cine
    0.05
    Act Density 0.025%

    No Known Activations