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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric literals (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    XP
    -0.07
    ENCED
    -0.07
    PLIER
    -0.06
     اصل
    -0.06
     harass
    -0.06
    Isl
    -0.06
    Lng
    -0.06
    룡
    -0.06
     střed
    -0.06
    анні
    -0.06
    POSITIVE LOGITS
    ٹ
    0.07
     &)
    0.07
    stellung
    0.07
    ）：
    0.06
    attributes
    0.06
     지역
    0.06
    cluding
    0.06
    °E
    0.06
    リー
    0.06
    toHave
    0.06
    Act Density 0.029%

    No Known Activations