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

    Neuronpedia

    INDEX
    Explanations

    う

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens (across different languages) that correspond to the adverb “yesterday.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     exclus
    -0.06
     стороны
    -0.06
     FilePath
    -0.06
     unnecessary
    -0.06
     brand
    -0.06
    には
    -0.06
     count
    -0.06
     Rectangle
    -0.06
     lot
    -0.06
     downloads
    -0.06
    POSITIVE LOGITS
    ΄
    0.07
    ,False
    0.07
    ób
    0.07
     defaultstate
    0.07
     "><
    0.07
    .Gray
    0.07
    /z
    0.06
     �
    0.06
    нять
    0.06
    scope
    0.06
    Act Density 0.051%

    No Known Activations