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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric tokens and numeric expressions (counts, years, ordinals, statistics) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    áli
    -0.07
     Jihad
    -0.07
    .questions
    -0.07
    .misc
    -0.07
    atatype
    -0.07
    (outfile
    -0.06
     цен
    -0.06
     unique
    -0.06
    ifr
    -0.06
    (isolate
    -0.06
    POSITIVE LOGITS
     asymmetric
    0.08
    :NSLocalizedString
    0.06
     abduction
    0.06
     Hall
    0.06
    GRID
    0.06
     Carla
    0.06
    	null
    0.06
    (Menu
    0.06
     directed
    0.06
     Garmin
    0.06
    Act Density 0.004%

    No Known Activations