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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron activates on the “v.” that appears in case captions (the “versus” marker between parties).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mx
    -0.07
     MATRIX
    -0.07
     Riverside
    -0.07
     pursuits
    -0.07
     matrices
    -0.07
    390
    -0.06
    .level
    -0.06
    Games
    -0.06
     activism
    -0.06
     муз
    -0.06
    POSITIVE LOGITS
     เข
    0.08
    ैं।↵↵
    0.06
     banks
    0.06
    )set
    0.06
     chặt
    0.06
    Sa
    0.06
    (command
    0.06
    “↵↵
    0.06
    $conn
    0.06
    spender
    0.06
    Act Density 0.003%

    No Known Activations