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

    Neuronpedia

    INDEX
    Explanations

    K

    np_max-act · gemini-2.0-flash

    This neuron never activates (all token activations are zero), so it doesn’t detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    otomy
    -0.07
     entend
    -0.07
     yet
    -0.06
     Trường
    -0.06
    终
    -0.06
    -0.06
    uses
    -0.06
    074
    -0.06
    igor
    -0.06
     Twe
    -0.06
    POSITIVE LOGITS
     pane
    0.06
    ayım
    0.06
     crisp
    0.06
    ,',
    0.06
     deceased
    0.06
    '',
    0.06
     Renault
    0.06
     Erect
    0.06
     Nude
    0.06
     '_',
    0.06
    Act Density 0.003%

    No Known Activations