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

    Neuronpedia

    INDEX
    Explanations

    the with

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numbers (decimal numeric tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _prices
    -0.06
    _note
    -0.06
     recruited
    -0.06
    Fi
    -0.06
    asier
    -0.06
     dří
    -0.06
     cu
    -0.06
     Ivy
    -0.06
     vascular
    -0.06
    譜
    -0.06
    POSITIVE LOGITS
     strategist
    0.07
    .eql
    0.07
    599
    0.06
    (egt
    0.06
     sinon
    0.06
    997
    0.06
    ................
    0.06
    ‎
    0.06
     ux
    0.06
    .sel
    0.06
    Act Density 0.103%

    No Known Activations