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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron detects numeric monetary amounts (numbers accompanied by currency symbols).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Klein
    -0.07
     Sachs
    -0.07
     passengers
    -0.06
    iring
    -0.06
    ForKey
    -0.06
     Bing
    -0.06
     jezd
    -0.06
    Big
    -0.06
     Flores
    -0.06
     pensions
    -0.06
    POSITIVE LOGITS
     především
    0.07
     collaborators
    0.07
     ZX
    0.06
    れた
    0.06
    ुं
    0.06
    ίδ
    0.06
    дн
    0.06
    .setup
    0.06
    лит
    0.06
    ckså
    0.06
    Act Density 0.115%

    No Known Activations