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

    Neuronpedia

    INDEX
    Explanations

    min

    np_max-act · gemini-2.0-flash

    This neuron detects precise floating-point numeric measurements (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ＊
    -0.07
    彡
    -0.06
    _locked
    -0.06
     coquine
    -0.06
    ﾟ
    -0.06
    apult
    -0.06
    >C
    -0.06
    "]="
    -0.06
     workspace
    -0.06
    =}
    -0.06
    POSITIVE LOGITS
    nger
    0.07
     výše
    0.06
    PATH
    0.06
    iề
    0.06
    _private
    0.06
    Access
    0.06
    ımı
    0.06
    _VALIDATE
    0.06
     sewer
    0.06
    .firstChild
    0.06
    Act Density 0.001%

    No Known Activations