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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/list markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     benign
    -0.08
    isira
    -0.08
     bachelor's
    -0.08
    geführt
    -0.08
    大陆
    -0.08
    quiera
    -0.07
     permiss
    -0.07
     инвалид
    -0.07
    各种
    -0.07
     katk
    -0.07
    POSITIVE LOGITS
     Tips
    0.13
     astuces
    0.12
    技巧
    0.11
     Tipps
    0.11
     �
    0.10
     Efficient
    0.10
    Tips
    0.10
     टिप
    0.10
     tips
    0.10
     Tricks
    0.09
    Act Density 0.065%

    No Known Activations