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

    Neuronpedia

    INDEX
    Explanations

    vitamin

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric measurement values (especially decimal‐formatted nutrient or concentration figures) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     الض
    -0.07
     Sale
    -0.07
     shard
    -0.07
    _RO
    -0.07
     clique
    -0.06
     endanger
    -0.06
    _np
    -0.06
     �
    -0.06
     เก
    -0.06
     debris
    -0.06
    POSITIVE LOGITS
     Vitamin
    0.16
     vitamin
    0.15
    itamin
    0.11
    amin
    0.08
     vitamins
    0.08
    vit
    0.08
     витами
    0.08
     pollut
    0.07
    vin
    0.07
     Twin
    0.07
    Act Density 0.004%

    No Known Activations