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

    Neuronpedia

    INDEX
    Explanations

    Names and Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pressure
    -0.07
    dül
    -0.07
    constitution
    -0.06
     Shortly
    -0.06
    紙
    -0.06
    вали
    -0.06
    立ち
    -0.06
     Frank
    -0.06
     congratulations
    -0.06
    ResourceId
    -0.06
    POSITIVE LOGITS
    typed
    0.07
     Hulu
    0.06
     '}↵
    0.06
     artworks
    0.06
     hide
    0.06
     picks
    0.06
     flip
    0.06
    aret
    0.06
    iếp
    0.06
    alore
    0.06
    Act Density 0.004%

    No Known Activations