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

    Neuronpedia

    INDEX
    Explanations

    people's full names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.63
     (
    0.54
     non
    0.53
    i
    0.52
     mixed
    0.51
     short
    0.50
     pure
    0.49
     top
    0.48
    ，
    0.47
     gre
    0.47
    POSITIVE LOGITS
     aventuras
    0.83
    Thoreau
    0.79
    <unused161>
    0.75
    nilvadipine
    0.75
    neutrophiles
    0.73
    itriangular
    0.73
     diamètre
    0.73
    SpringMVCProject
    0.73
    Benzoimidazole
    0.72
    TGFuZ
    0.71
    Act Density 0.006%

    No Known Activations