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

    Neuronpedia

    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    ']").
    -0.06
    Queen
    -0.06
    كية
    -0.06
    оф
    -0.06
    ruit
    -0.06
    Kevin
    -0.05
    ัฐ
    -0.05
    _lua
    -0.05
    Turning
    -0.05
    POSITIVE LOGITS
     Erd
    0.07
    μές
    0.07
    MDB
    0.07
    ningar
    0.07
     عرضه
    0.06
     set
    0.06
    (nr
    0.06
    0.06
     абсолютно
    0.06
     Emb
    0.06
    Act Density 0.006%

    No Known Activations