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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash

    This neuron never responds (all activations are zero) and thus doesn’t appear to detect any feature.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ursions
    -0.07
     Geo
    -0.07
     kultur
    -0.07
    ees
    -0.07
     Fut
    -0.06
    考试
    -0.06
     mayoría
    -0.06
    904
    -0.06
    Tier
    -0.06
     Semantic
    -0.06
    POSITIVE LOGITS
    ／/
    0.06
    ุงเทพ
    0.06
    $db
    0.06
    する
    0.06
     UIResponder
    0.06
     moth
    0.06
     tonumber
    0.06
    ～～
    0.06
    \\
    0.06
    (Vertex
    0.06
    Act Density 0.011%

    No Known Activations