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

    Neuronpedia

    INDEX
    Explanations

    Montreal tomorrow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    리
    0.90
    ing
    0.88
    ри
    0.81
    ě
    0.79
     слегка
    0.78
    ast
    0.77
    ä
    0.77
    ಲ
    0.77
    ,’
    0.75
     réduit
    0.75
    POSITIVE LOGITS
    t
    1.21
     Montreal
    0.97
     to
    0.89
     inim
    0.84
    ﺍ
    0.82
     Argentina
    0.78
    Montreal
    0.78
    𝘴
    0.78
    י
    0.77
     oriental
    0.76
    Act Density 0.004%

    No Known Activations