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

    Neuronpedia

    INDEX
    Explanations

    comparisons and differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aimed
    -0.07
     Cornell
    -0.07
    legs
    -0.06
    Bạn
    -0.06
    Latest
    -0.06
    Peter
    -0.06
    "L
    -0.06
     Gum
    -0.06
     unbe
    -0.06
    Fun
    -0.06
    POSITIVE LOGITS
    .ScrollBars
    0.07
     :/:
    0.07
    .textLabel
    0.07
     киш
    0.06
    /platform
    0.06
     погляд
    0.06
    ял
    0.06
     :'
    0.06
    Milliseconds
    0.06
    ((&
    0.06
    Act Density 0.089%

    No Known Activations