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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the phrase “presented the same way as in the document,” i.e. when checking consistency of entity name presentation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    apas
    -0.08
    isure
    -0.07
     христи
    -0.07
     melanch
    -0.07
    -sensitive
    -0.06
     pil
    -0.06
    OLER
    -0.06
     शत
    -0.06
    Explorer
    -0.06
    ्वत
    -0.06
    POSITIVE LOGITS
     마지막
    0.07
    mA
    0.06
    BlockSize
    0.06
    (group
    0.06
     confidently
    0.06
     가정
    0.06
    렇게
    0.06
    ...)
    0.06
    .callback
    0.06
    Ind
    0.05
    Act Density 0.001%

    No Known Activations