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

    Neuronpedia

    INDEX
    Explanations

    lookup

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “lookup” (and its variants like “look up” or “looks up”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Arn
    -0.07
     sent
    -0.07
     boat
    -0.07
    全部
    -0.07
     mist
    -0.07
     arm
    -0.07
     cr
    -0.06
     minimize
    -0.06
     Band
    -0.06
    玲
    -0.06
    POSITIVE LOGITS
     lookup
    0.09
     Lookup
    0.08
    Lookup
    0.08
    lookup
    0.07
     uphol
    0.07
    _lookup
    0.07
     Roth
    0.07
    hof
    0.07
     UM
    0.07
     �
    0.07
    Act Density 0.005%

    No Known Activations