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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash

    The neuron activates on temporal expressions—especially month names and associated date numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dünya
    -0.06
     Belediyesi
    -0.06
    もり
    -0.06
    INPUT
    -0.06
    	else
    -0.06
     школ
    -0.06
     planned
    -0.06
     düzenli
    -0.06
     Authority
    -0.06
    	panic
    -0.06
    POSITIVE LOGITS
    Returns
    0.07
     iov
    0.07
    iagnostics
    0.07
    أن
    0.06
    scan
    0.06
     člov
    0.06
    ця
    0.06
    Ν
    0.06
    Hardware
    0.06
    /block
    0.06
    Act Density 0.051%

    No Known Activations