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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron is detecting the first content word at the start of an answer or major explanatory sentence.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gujar
    -0.07
    ictureBox
    -0.06
    Skills
    -0.06
    yect
    -0.06
    iyan
    -0.06
    _layers
    -0.06
    _CARD
    -0.06
    .docs
    -0.06
    .Acc
    -0.06
     UserRole
    -0.06
    POSITIVE LOGITS
    يب
    0.07
     flawless
    0.07
     IA
    0.06
    átní
    0.06
    union
    0.06
     سطح
    0.06
    머니
    0.06
     conventional
    0.06
     lens
    0.06
    (sp
    0.06
    Act Density 0.109%

    No Known Activations