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

    Neuronpedia

    INDEX
    Explanations

    atoms and ions

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on occurrences of the word “atom” (and closely related forms like “atoms”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     леч
    -0.07
     таб
    -0.07
    elsius
    -0.06
    Tabla
    -0.06
    heits
    -0.06
     autoplay
    -0.06
    okino
    -0.06
     Ctrl
    -0.06
    eti
    -0.06
    _invoice
    -0.06
    POSITIVE LOGITS
     лит
    0.08
    ù
    0.07
     Kent
    0.07
     sampling
    0.07
    ри
    0.07
    -calendar
    0.07
     polling
    0.07
    Sampling
    0.06
     discusses
    0.06
    Net
    0.06
    Act Density 0.011%

    No Known Activations