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

    Neuronpedia

    INDEX
    Explanations

    quant analysis, super computing

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on tokens containing the substring "quant" (e.g., "quant", "Quant", "Quantum"), i.e., references to quantitative/quant/quantum.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    grpc
    0.47
    toByteArray
    0.46
    saa
    0.44
    ր
    0.44
    ϫ
    0.44
     generales
    0.44
     decim
    0.43
    ibili
    0.43
    ស៊ី
    0.43
    кли
    0.42
    POSITIVE LOGITS
     Arizona
    0.66
     Nevada
    0.58
     Alabama
    0.57
     Oklahoma
    0.56
    Alabama
    0.56
    Modern
    0.54
    Michigan
    0.53
    Arizona
    0.52
     Mexico
    0.52
     Iowa
    0.52
    Act Density 0.001%

    No Known Activations