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

    Neuronpedia

    INDEX
    Explanations

    uses or appears

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    举行
    -0.08
     sometime
    -0.08
     viable
    -0.08
    吧
    -0.08
    ）（
    -0.08
    оп
    -0.08
    ：https
    -0.08
    -worthy
    -0.08
     malfunction
    -0.08
     docking
    -0.08
    POSITIVE LOGITS
     clauses
    0.09
     braces
    0.09
     parentheses
    0.09
     denominator
    0.08
     Terms
    0.08
     seemingly
    0.08
     numerator
    0.08
     terms
    0.08
     squared
    0.07
    ials
    0.07
    Act Density 0.120%

    No Known Activations