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

    Neuronpedia

    INDEX
    Explanations

    adjectives followed by suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wildly
    0.83
     strongly
    0.75
     Artinya
    0.73
     पूरी
    0.73
    িকভাবে
    0.72
    strongly
    0.72
    强烈
    0.71
     усилия
    0.69
    quite
    0.69
     quite
    0.68
    POSITIVE LOGITS
    ening
    2.48
    ened
    2.38
    ness
    2.29
    est
    2.11
    nesses
    2.08
    eners
    2.03
    ens
    1.81
    ener
    1.66
    ENING
    1.65
    NESS
    1.55
    Act Density 0.678%

    No Known Activations