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

    Neuronpedia

    INDEX
    Explanations

    Negation/exclusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    灭
    -0.06
     encontr
    -0.06
     му
    -0.06
     سنت
    -0.06
     Resource
    -0.06
     подраз
    -0.06
     aydın
    -0.06
     manifest
    -0.06
     dů
    -0.06
    meyi
    -0.06
    POSITIVE LOGITS
    Tokenizer
    0.07
    tein
    0.07
     —
    0.07
    |)↵
    0.07
     Aristotle
    0.07
    [float
    0.06
     dataGridView
    0.06
     سه
    0.06
     �
    0.06
    opcode
    0.06
    Act Density 0.004%

    No Known Activations