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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    This neuron activates predominantly on numeric tokens (digits and decimal number fragments) in tables.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iphone
    -0.07
    Animated
    -0.07
    .touches
    -0.07
    =read
    -0.06
    áticas
    -0.06
    irket
    -0.06
    inder
    -0.06
    owl
    -0.06
    重点
    -0.06
    imagem
    -0.06
    POSITIVE LOGITS
    +'\
    0.07
     TextStyle
    0.06
    ポート
    0.06
    xico
    0.06
     Sym
    0.06
     ApiResponse
    0.06
     BBB
    0.06
    ?’
    0.06
    156
    0.06
    +\
    0.06
    Act Density 0.006%

    No Known Activations