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

    Neuronpedia

    INDEX
    Explanations

    geometrical definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ாள்
    -0.08
     Yer
    -0.07
     itin
    -0.07
    빙
    -0.07
    -0.07
     fant
    -0.07
     देती
    -0.07
    'att
    -0.07
     Ana
    -0.07
     leaderboard
    -0.07
    POSITIVE LOGITS
    /examples
    0.09
    状態
    0.09
     classification
    0.09
    cases
    0.09
     outright
    0.08
     бывают
    0.08
    Degrees
    0.08
    остоя
    0.08
    examples
    0.08
    classification
    0.08
    Act Density 0.014%
    No Known Activations