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

    Neuronpedia

    INDEX
    Explanations

    Guild

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nature
    -0.08
    powiedź
    -0.08
     Tet
    -0.07
    TT
    -0.07
    赍
    -0.07
    Math
    -0.07
    전자
    -0.07
    ']].
    -0.07
    لجنة
    -0.07
    lore
    -0.07
    POSITIVE LOGITS
     Citadel
    0.08
     Guild
    0.07
      ↵
    0.07
     Templ
    0.07
     grid
    0.07
    实例
    0.07
     직
    0.07
    calendar
    0.07
    읻
    0.07
    (il
    0.06
    Act Density 0.002%

    No Known Activations