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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron detects capitalized proper names—e.g. band or organization names—across the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    >j
    -0.07
     PACKAGE
    -0.06
    ournals
    -0.06
    quirer
    -0.06
    管理员
    -0.06
    )))↵↵
    -0.06
     Bilim
    -0.06
    Steel
    -0.06
    inux
    -0.06
    评论
    -0.06
    POSITIVE LOGITS
    ******
↵
    0.07
     einmal
    0.07
    .Engine
    0.07
    нулась
    0.07
     spurred
    0.06
    (rr
    0.06
    (Uri
    0.06
     tasked
    0.06
    Soph
    0.06
     التر
    0.06
    Act Density 0.114%

    No Known Activations