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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sym
    -0.07
    VarChar
    -0.07
     Crew
    -0.07
     граж
    -0.06
    四项
    -0.06
    ategic
    -0.06
    衍生
    -0.06
    战略性
    -0.06
    .getElementsByClassName
    -0.06
    human
    -0.06
    POSITIVE LOGITS
    assi
    0.07
     crackers
    0.07
     faut
    0.07
     Sark
    0.07
     popup
    0.06
    .Servlet
    0.06
    iện
    0.06
     abolish
    0.06
    ؍
    0.06
    🖒
    0.06
    Act Density 0.047%

    No Known Activations