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

    Neuronpedia

    INDEX
    Explanations

    Sudoku puzzles

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “sudoku” (especially in the context of writing or requesting a Sudoku solver script).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ow
    -0.07
     Jer
    -0.07
     ممکن
    -0.06
    OVÁ
    -0.06
    �数
    -0.06
    Threads
    -0.06
     ents
    -0.06
    imators
    -0.06
     evapor
    -0.06
    Cast
    -0.06
    POSITIVE LOGITS
     angi
    0.07
    거
    0.07
     alma
    0.07
    InterfaceOrientation
    0.06
    lüğ
    0.06
     ePub
    0.06
     พฤศจ
    0.06
    antd
    0.06
    \Requests
    0.06
     Mentor
    0.06
    Act Density 0.007%

    No Known Activations