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

    Neuronpedia

    INDEX
    Explanations

    subject matter expert or spokesman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    1.05
    er
    1.02
    اً
    0.98
    0
    0.93
    t
    0.92
    ;
    0.92
    l
    0.91
    ุ
    0.90
    _
    0.89
    اک
    0.89
    POSITIVE LOGITS
    س
    0.84
    сную
    0.79
    ள்
    0.77
    с
    0.75
    ()}
    0.73
     ευ
    0.70
     aimer
    0.70
    憬
    0.68
     akkor
    0.68
     aix
    0.67
    Act Density 0.000%

    No Known Activations