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

    Neuronpedia

    INDEX
    Explanations

    more comparative descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OR
    1.98
    郸
    1.98
    OUND
    1.95
    ु
    1.95
    우스
    1.93
     গিয়া
    1.93
    ILLIPS
    1.89
    EMPL
    1.88
    ▟
    1.88
     zostanie
    1.83
    POSITIVE LOGITS
     importantly
    2.50
    ことを
    2.20
    ق
    2.16
     allá
    2.05
     iż
    2.00
     Importantly
    1.95
    いった
    1.80
    ad
    1.77
     superficially
    1.77
    ový
    1.77
    Act Density 0.356%

    No Known Activations