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

    Neuronpedia

    INDEX
    Explanations

    trailing

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “trailing.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gắng
    -0.07
    442
    -0.07
    وة
    -0.07
    onian
    -0.07
     convergence
    -0.07
    _characters
    -0.06
    dě
    -0.06
    beat
    -0.06
     exempt
    -0.06
     Russians
    -0.06
    POSITIVE LOGITS
     trailing
    0.08
     Blizzard
    0.07
    Tri
    0.06
    (Pointer
    0.06
    _bl
    0.06
     توضی
    0.06
     aydın
    0.06
    	printk
    0.06
     μαζί
    0.06
    piel
    0.06
    Act Density 0.002%

    No Known Activations