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

    Neuronpedia

    INDEX
    Explanations

    algebraic expressions

    np_max-act · gemini-2.0-flash

    This neuron activates on decimal-number tokens (numeric constants containing a decimal point) within mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    XmlElement
    -0.07
    voice
    -0.06
    .score
    -0.06
    /blob
    -0.06
     Parses
    -0.06
    piler
    -0.06
    еної
    -0.06
    knife
    -0.06
     Queue
    -0.06
    word
    -0.06
    POSITIVE LOGITS
    品牌
    0.07
    bbox
    0.07
     �
    0.06
     SSL
    0.06
    .checkBox
    0.06
    cesso
    0.06
    slick
    0.06
     cerebral
    0.06
     bütün
    0.06
    权限
    0.06
    Act Density 0.009%

    No Known Activations