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

    Neuronpedia

    INDEX
    Explanations

    mechanisms

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “molecular mechanisms” (and closely related technical phrasing).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     numbering
    -0.07
     Ukrain
    -0.07
     Programmer
    -0.07
     HttpServlet
    -0.06
     Winners
    -0.06
    ===
    -0.06
    邮箱
    -0.06
    ectors
    -0.06
    (cmp
    -0.06
    url
    -0.06
    POSITIVE LOGITS
     disturbed
    0.07
    	angle
    0.07
     انواع
    0.07
    _unc
    0.06
    pes
    0.06
    افی
    0.06
    .Keyword
    0.06
    就在
    0.06
     chce
    0.06
     �
    0.06
    Act Density 0.014%

    No Known Activations