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

    Neuronpedia

    INDEX
    Explanations

    pre

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the substring “pre” (as in pre-compiled, pre-recorded, pre-packaged, etc.), i.e., words beginning with the prefix “pre.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    angkan
    -0.07
    wa
    -0.07
    �
    -0.06
     liquids
    -0.06
    ONLY
    -0.06
    iveness
    -0.06
     governmental
    -0.06
    스타
    -0.06
    řít
    -0.06
     beverages
    -0.06
    POSITIVE LOGITS
    .Maximum
    0.08
     pre
    0.07
    (return
    0.07
    	glEnable
    0.06
    aside
    0.06
    _hom
    0.06
     hom
    0.06
     prer
    0.06
    .TO
    0.06
    lt
    0.06
    Act Density 0.012%

    No Known Activations