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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron detects URL query parameters that represent software version numbers (e.g. “v=3.5078125” or “4.2.3”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CY
    -0.07
    .flag
    -0.06
     asm
    -0.06
     Hi
    -0.06
    folder
    -0.06
    407
    -0.06
     rer
    -0.06
    .getBody
    -0.06
     Ryan
    -0.06
    .FieldName
    -0.06
    POSITIVE LOGITS
     اخت
    0.08
    SDK
    0.07
    illions
    0.07
    -->
↵
    0.07
     необходим
    0.07
    _MR
    0.07
     فکی
    0.07
     doz
    0.06
    )','
    0.06
    .health
    0.06
    Act Density 0.002%

    No Known Activations