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

    Neuronpedia

    INDEX
    Explanations

    UI interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    描
    -0.08
     ethics
    -0.08
     influ
    -0.08
    力量
    -0.08
     ethical
    -0.08
     presença
    -0.08
     মহ
    -0.08
     controvers
    -0.08
    -0.07
    基
    -0.07
    POSITIVE LOGITS
     cumbersome
    0.13
     Browse
    0.11
     browsing
    0.11
     просмотр
    0.11
     tedious
    0.10
     hassle
    0.10
     Quickly
    0.10
     ausprobieren
    0.10
     clicar
    0.10
     클릭
    0.10
    Act Density 0.040%
    No Known Activations