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

    Neuronpedia

    INDEX
    Explanations

    captions, short descriptions, statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fähigkeit
    -0.09
     prerequisite
    -0.08
     Dependency
    -0.08
     vigilant
    -0.08
     :-)
    -0.08
     resolución
    -0.08
     foreseeable
    -0.08
     Damage
    -0.07
    .grp
    -0.07
    fähig
    -0.07
    POSITIVE LOGITS
     accompanying
    0.12
    説明
    0.11
     accompany
    0.11
    文字
    0.11
     accompanies
    0.10
     captions
    0.10
     설명
    0.09
     accompagne
    0.09
     açıkl
    0.09
    ед
    0.09
    Act Density 0.089%

    No Known Activations