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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on second-person address words (e.g. “you,” “your”) and related reader-directed phrasing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Austria
    -0.07
     Helena
    -0.06
    verture
    -0.06
     Indust
    -0.06
     Advent
    -0.06
    strup
    -0.06
     turtles
    -0.06
    nice
    -0.06
    менш
    -0.06
     jugar
    -0.06
    POSITIVE LOGITS
    .serialize
    0.07
    _BAR
    0.06
     knull
    0.06
     glow
    0.06
    (ex
    0.06
    тобы
    0.06
     Median
    0.06
    /runtime
    0.06
    .Quad
    0.06
    (Font
    0.06
    Act Density 0.018%

    No Known Activations