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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric expressions—especially counts, percentages, and decimal‐formatted statistics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to patient outcomes in medical studies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Wu
    -0.07
     Jul
    -0.07
    Gain
    -0.07
    indexes
    -0.07
    Never
    -0.07
    Get
    -0.07
     Marijuana
    -0.07
     Gonzalez
    -0.07
    max
    -0.07
    missions
    -0.06
    POSITIVE LOGITS
     cherished
    0.07
    185
    0.07
     fortn
    0.07
     birlik
    0.07
     Fay
    0.07
    Facing
    0.07
    ồ
    0.07
     podnik
    0.07
     fond
    0.06
     Admir
    0.06
    Act Density 0.098%

    No Known Activations