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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on floating-point numeric literals (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .modified
    -0.07
    _TV
    -0.06
    DEFAULT
    -0.06
    ="#"
    -0.06
     поз
    -0.06
    (resourceName
    -0.06
    Ό
    -0.06
    _GROUPS
    -0.06
     heuristic
    -0.06
     انتخاب
    -0.06
    POSITIVE LOGITS
    SCII
    0.07
     RCMP
    0.06
     DER
    0.06
     Produkt
    0.06
    _wifi
    0.06
    eně
    0.06
     submarine
    0.06
    τή
    0.06
     SSP
    0.06
    虫
    0.06
    Act Density 0.032%

    No Known Activations