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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash

    The neuron responds to bits of quoted speech attribution, especially the word “said” and surrounding quotation marks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    visual
    -0.07
     친
    -0.06
    _CUDA
    -0.06
    IPAddress
    -0.06
    udy
    -0.06
    诺
    -0.06
     spices
    -0.06
    Argentina
    -0.06
     touring
    -0.06
    /script
    -0.06
    POSITIVE LOGITS
    :".
    0.07
     ре
    0.06
     customs
    0.06
     �
    0.06
     Derm
    0.06
    ."+
    0.06
    азвание
    0.06
    -destruct
    0.06
     RM
    0.06
     Negative
    0.06
    Act Density 0.051%

    No Known Activations