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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “index” (especially in the phrase “index theorem”) and thus is detecting references to index theorems or index-related concepts in mathematical contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cedes
    -0.06
    .integration
    -0.06
    タル
    -0.06
    λος
    -0.06
    roveň
    -0.06
    apon
    -0.06
    �乐
    -0.06
    ]},
    -0.05
    (Login
    -0.05
    createTime
    -0.05
    POSITIVE LOGITS
     Photography
    0.07
    �
    0.07
    .opts
    0.07
    이었
    0.06
    _af
    0.06
    Expression
    0.06
     граду
    0.06
    _FIELD
    0.06
    $product
    0.06
    ektör
    0.06
    Act Density 0.012%

    No Known Activations