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

    Neuronpedia

    INDEX
    Explanations

    hunt

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens, especially decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    dev
    -0.06
    "id
    -0.06
    .Exec
    -0.06
    τού
    -0.06
    anych
    -0.06
     رفته
    -0.06
    (sheet
    -0.05
    "A
    -0.05
     střed
    -0.05
     वस
    -0.05
    POSITIVE LOGITS
    虚
    0.08
     pro
    0.07
    -big
    0.07
    encodeURIComponent
    0.07
    \data
    0.07
     Mod
    0.06
    .STATE
    0.06
    (?:
    0.06
    	FOR
    0.06
     DIG
    0.06
    Act Density 0.014%

    No Known Activations