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

    Neuronpedia

    INDEX
    Explanations

    search

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the predefined tool names in the tool list (e.g. “FinanceTool,” “ProductSearch,” “JobTool,” “TripTool,” “PDF&URLTool”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Sect
    -0.07
    gratis
    -0.07
    Fabric
    -0.07
     Основ
    -0.07
     macht
    -0.06
     Gorgeous
    -0.06
     Mango
    -0.06
     žád
    -0.06
    imators
    -0.06
    POSITIVE LOGITS
    些
    0.07
     search
    0.06
    (expect
    0.06
    CAD
    0.06
     ancestor
    0.06
    _AXIS
    0.06
     scraps
    0.06
     investigations
    0.06
     çoğu
    0.06
     getTitle
    0.06
    Act Density 0.006%

    No Known Activations