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

    Neuronpedia

    INDEX
    Explanations

    descriptions/actions/sensory details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     covariance
    -0.08
     ış
    -0.08
    adians
    -0.08
     aura
    -0.08
     pedigree
    -0.08
     Website
    -0.07
     pada
    -0.07
    Apart
    -0.07
     horm
    -0.07
     Spotlight
    -0.07
    POSITIVE LOGITS
     chewing
    0.14
     swallowing
    0.13
     saliva
    0.13
    喝
    0.13
    饮
    0.13
     drinking
    0.13
     uống
    0.12
    飲
    0.12
    嘴
    0.12
    吐
    0.11
    Act Density 0.058%

    No Known Activations