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

    Neuronpedia

    INDEX
    Explanations

    stylesheet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     науки
    -0.06
    icích
    -0.06
    て
    -0.06
    ymb
    -0.06
    DataSet
    -0.06
     isize
    -0.06
     seni
    -0.06
    medicine
    -0.06
     resizeMode
    -0.06
     střed
    -0.06
    POSITIVE LOGITS
     Penguins
    0.07
    _Point
    0.07
     ст
    0.07
    Offer
    0.07
     sink
    0.07
     struck
    0.06
    攻击
    0.06
    enguins
    0.06
     handicap
    0.06
    Super
    0.06
    Act Density 0.001%

    No Known Activations