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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash

    This neuron fires on LaTeX‐style tensor notation, spotting uppercase tensor symbols (like A, B) with subscripts/superscripts and the “:” double‐dot product operator within math expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _import
    -0.06
     cooked
    -0.06
    우
    -0.06
     We
    -0.06
    content
    -0.06
     we
    -0.06
    -st
    -0.06
    He
    -0.06
     ры
    -0.06
     orbit
    -0.06
    POSITIVE LOGITS
    AspectRatio
    0.07
    tığ
    0.07
    .mousePosition
    0.06
    createdAt
    0.06
    illance
    0.06
    .offsetWidth
    0.06
     UIGraphics
    0.06
    Fecha
    0.06
    _kategori
    0.06
     donating
    0.06
    Act Density 0.011%

    No Known Activations