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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron is keyed to recognize numeric tokens (years, measurements, and other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gods
    -0.06
    _det
    -0.06
    acím
    -0.06
     Priv
    -0.06
     diagnostic
    -0.06
    Ê
    -0.06
     Kol
    -0.06
     Undo
    -0.06
     possession
    -0.06
     jó
    -0.06
    POSITIVE LOGITS
     anlay
    0.07
    ujet
    0.07
    	freopen
    0.07
    :NSLocalizedString
    0.06
     knockout
    0.06
     "{$
    0.06
     dří
    0.06
    े.
    0.06
     */,
    0.06
     masse
    0.06
    Act Density 0.042%

    No Known Activations