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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron activates on the phrase “It’s a” at the beginning of a clause.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Verts
    -0.07
     hâl
    -0.07
    Has
    -0.07
    修改
    -0.06
    xx
    -0.06
    :Is
    -0.06
     �
    -0.06
    	If
    -0.06
    کتر
    -0.06
     wc
    -0.06
    POSITIVE LOGITS
    b
    0.06
     Squ
    0.06
     asym
    0.06
    	done
    0.06
     menggunakan
    0.06
    ayan
    0.06
    537
    0.06
    xEA
    0.05
    >B
    0.05
     Barney
    0.05
    Act Density 0.059%

    No Known Activations