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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plannen
    -0.08
     graded
    -0.08
     celebrated
    -0.07
     obsah
    -0.07
     યોજ
    -0.07
     cens
    -0.07
    fos
    -0.07
     purchase
    -0.07
     تشمل
    -0.07
    .mutable
    -0.07
    POSITIVE LOGITS
     Threads
    0.09
    에서
    0.08
    曰
    0.08
    에서는
    0.08
    中新
    0.08
     -"
    0.08
    がお送りします
    0.08
    老板
    0.08
     Raymond
    0.08
    .Warn
    0.08
    Act Density 0.008%

    No Known Activations