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

    Neuronpedia

    INDEX
    Explanations

    address/location format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ඬ
    0.83
    łeś
    0.75
     ricordare
    0.72
     conoscere
    0.71
    реди
    0.68
    uole
    0.66
    leigh
    0.64
    timezone
    0.63
     Commonly
    0.63
     Someone
    0.62
    POSITIVE LOGITS
     tenets
    0.75
     aimed
    0.72
     albeit
    0.69
     thereby
    0.66
     strive
    0.65
    haust
    0.64
     algorithm
    0.63
     tasked
    0.62
     procurement
    0.62
     IMAX
    0.62
    Act Density 0.001%

    No Known Activations