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

    Neuronpedia

    INDEX
    Explanations

    historic locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Helpful
    -0.09
     Helpful
    -0.08
     XOR
    -0.08
     معدل
    -0.08
     ICS
    -0.08
     iris
    -0.08
     OPT
    -0.08
     hilfreich
    -0.07
     helpful
    -0.07
     simpt
    -0.07
    POSITIVE LOGITS
    历史
    0.19
     history
    0.16
    歷
    0.16
     ইতিহাস
    0.16
     geschiedenis
    0.16
     इतिहास
    0.16
     ചരിത്ര
    0.16
     historiques
    0.16
     historical
    0.16
     историю
    0.15
    Act Density 0.031%

    No Known Activations