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

    Neuronpedia

    INDEX
    Explanations

    stuck seeking ideas or help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বর্তমান
    0.71
    FY
    0.67
     learn
    0.67
     CAGR
    0.67
     बारीक
    0.67
    Learn
    0.67
     whereby
    0.65
    aughan
    0.65
    也可以
    0.65
    ниш
    0.65
    POSITIVE LOGITS
     Gave
    0.92
     jab
    0.89
     knelt
    0.89
     poppies
    0.84
     sculptures
    0.83
    gave
    0.83
     gave
    0.81
    
    0.81
     crus
    0.81
     jabs
    0.80
    Act Density 0.003%

    No Known Activations