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

    Neuronpedia

    INDEX
    Explanations

    が

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up only on numeric tokens that include a decimal point, i.e. floating-point literals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cr
    -0.06
    tool
    -0.06
     inconvenient
    -0.06
    -other
    -0.06
    _topics
    -0.06
     letto
    -0.06
     bm
    -0.06
    bright
    -0.06
     deceased
    -0.06
     بیمه
    -0.06
    POSITIVE LOGITS
    RIA
    0.07
    igInteger
    0.06
     그가
    0.06
     врем
    0.06
     Deliver
    0.06
    858
    0.06
    скому
    0.06
    ria
    0.06
    256
    0.06
    بع
    0.06
    Act Density 0.179%

    No Known Activations