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

    Neuronpedia

    INDEX
    Explanations

    Random strings/code

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (sequences of digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ตน
    -0.07
    illusion
    -0.06
     AREA
    -0.06
     poignant
    -0.06
     order
    -0.06
     DVD
    -0.06
    -tw
    -0.06
     myself
    -0.06
    _INSTANCE
    -0.06
     Lexer
    -0.06
    POSITIVE LOGITS
     torino
    0.06
     stojí
    0.06
     xpath
    0.06
     CHtml
    0.06
    _parameter
    0.06
     آسیاب
    0.06
    pcion
    0.06
     bindActionCreators
    0.06
     geçen
    0.06
    áj
    0.06
    Act Density 0.022%

    No Known Activations