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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash

    The neuron fires on date expressions—specifically on day‐of‐month numbers (often in “on <day> <Month>” constructs).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lob
    -0.08
     edip
    -0.06
     chests
    -0.06
     stealing
    -0.06
     karar
    -0.06
     neg
    -0.06
    Usage
    -0.06
    技能
    -0.06
     DH
    -0.06
    	raise
    -0.06
    POSITIVE LOGITS
    =\""
    0.08
    >';↵
    0.07
    Рµ
    0.06
     VERIFY
    0.06
     '↵
    0.06
     WE
    0.06
    _ASSOC
    0.06
    ._↵↵
    0.06
    ា
    0.06
     لباس
    0.06
    Act Density 0.009%

    No Known Activations