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

    Neuronpedia

    INDEX
    Explanations

    Comparisons, code, and analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eterminate
    -0.07
    .firebase
    -0.07
    .Diagnostics
    -0.06
    antity
    -0.06
    .Texture
    -0.06
    erialize
    -0.06
     thể
    -0.06
     Voy
    -0.06
    .cell
    -0.06
     ü
    -0.06
    POSITIVE LOGITS
     ）↵
    0.07
     حکومت
    0.07
    _skb
    0.07
     أبريل
    0.07
     марта
    0.06
    Section
    0.06
    ३
    0.06
     Ends
    0.06
    �
    0.06
     weiber
    0.06
    Act Density 0.126%

    No Known Activations