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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    评
    -0.07
     bump
    -0.07
     κ
    -0.06
     бума
    -0.06
     newspapers
    -0.06
    tolower
    -0.06
     lekker
    -0.06
     Nil
    -0.06
    郭
    -0.06
     přece
    -0.06
    POSITIVE LOGITS
     ReadOnly
    0.08
    ReadOnly
    0.07
    _keys
    0.07
    -way
    0.07
     pry
    0.07
     dados
    0.06
     Valid
    0.06
    addy
    0.06
    บบ
    0.06
    airo
    0.06
    Act Density 0.002%

    No Known Activations