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

    Neuronpedia

    INDEX
    Explanations

    Credit limits and scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    收藏
    -0.08
    Gif
    -0.08
     vowel
    -0.08
     schlechte
    -0.08
     schlechten
    -0.08
     ered
    -0.07
     gründ
    -0.07
    Golden
    -0.07
     profit
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    额度
    0.14
     Maximum
    0.11
    .Maximum
    0.11
     Capacity
    0.10
     exceed
    0.10
     capacity
    0.10
    容量
    0.10
     límites
    0.10
     limites
    0.09
     maxi
    0.09
    Act Density 0.011%

    No Known Activations