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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aggreg
    -0.08
    评
    -0.08
     emotion
    -0.07
    Aggreg
    -0.07
     الاجتماعي
    -0.07
    ·
    -0.07
     öld
    -0.07
     killer
    -0.07
     psyched
    -0.07
    psych
    -0.07
    POSITIVE LOGITS
     repres
    0.09
     orientations
    0.08
     Coordinates
    0.08
     acreditar
    0.08
     simpl
    0.08
     inclined
    0.08
     uusia
    0.08
    _COORD
    0.08
     coordinates
    0.08
     conveniently
    0.08
    Act Density 0.018%

    No Known Activations