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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on occurrences of the word “where.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -period
    -0.07
    .Add
    -0.06
     Late
    -0.06
    اکی
    -0.06
    -volume
    -0.06
    (job
    -0.06
    яд
    -0.06
     unit
    -0.06
     желуд
    -0.06
    料無料
    -0.06
    POSITIVE LOGITS
     where
    0.11
     donde
    0.08
     hvor
    0.07
     Westminster
    0.07
    	where
    0.07
    liament
    0.06
     protestors
    0.06
     steam
    0.06
    emplates
    0.06
     WHERE
    0.06
    Act Density 0.037%

    No Known Activations