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

    Neuronpedia

    INDEX
    Explanations

    US states and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.20
    etition
    1.13
    ができ
    1.09
    an
    1.02
    ución
    1.02
    anía
    1.02
    ेच्छा
    0.99
    et
    0.98
     Tutti
    0.97
    etl
    0.96
    POSITIVE LOGITS
    לים
    1.09
    시아
    0.99
    襞
    0.99
    stava
    0.98
     caranya
    0.98
    ደር
    0.98
     booklet
    0.96
    ‍♂️
    0.94
    ಯಲ್ಲಿ
    0.94
    citing
    0.93
    Act Density 0.018%

    No Known Activations