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

    Neuronpedia

    INDEX
    Explanations

    wonderful greetings and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.43
    2
    1.27
    t
    1.15
     on
    0.96
    ’
    0.95
    ng
    0.89
    s
    0.89
     at
    0.85
    ,
    0.84
    the
    0.83
    POSITIVE LOGITS
    padă
    0.88
    ي
    0.85
     Франции
    0.84
     Сури
    0.82
    لي
    0.77
    ير
    0.77
    し
    0.77
    瑪
    0.76
     Besonders
    0.75
    ورك
    0.75
    Act Density 0.012%

    No Known Activations