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

    Neuronpedia

    INDEX
    Explanations

    cooking recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Day
    -0.07
     trophy
    -0.07
     sponsor
    -0.06
     ring
    -0.06
    Definitions
    -0.06
     と
    -0.06
     watches
    -0.06
    Numbers
    -0.06
     symmetry
    -0.06
    .author
    -0.06
    POSITIVE LOGITS
    ハイ
    0.07
     증가
    0.07
     країн
    0.07
     yaşlı
    0.07
     savun
    0.06
     closeModal
    0.06
    Sheet
    0.06
     유지
    0.06
    感じ
    0.06
    ший
    0.06
    Act Density 0.007%

    No Known Activations