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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     duplic
    -0.07
     Pett
    -0.07
    _inverse
    -0.06
     ether
    -0.06
    _perc
    -0.06
    MED
    -0.06
     Also
    -0.06
     WAS
    -0.06
    Img
    -0.06
    ContentType
    -0.06
    POSITIVE LOGITS
     resulting
    0.07
     edip
    0.07
    _INCREF
    0.07
     güven
    0.06
     consegu
    0.06
     ตาม
    0.06
    湖
    0.06
    acak
    0.06
    .onViewCreated
    0.06
     вида
    0.06
    Act Density 0.023%

    No Known Activations