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

    Neuronpedia

    INDEX
    Explanations

    poiled/CO2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    De
    0.65
    B
    0.54
    Pre
    0.52
    El
    0.52
    D
    0.51
    IO
    0.51
    Fine
    0.51
    Edit
    0.49
    Ocean
    0.49
    Curt
    0.49
    POSITIVE LOGITS
     तुम्ह
    0.54
     Besuch
    0.52
     вам
    0.49
     நீங்கள்
    0.49
    ى
    0.48
     bạn
    0.48
     तुम्हाला
    0.47
     fxg
    0.47
     તમને
    0.46
    𝐡
    0.45
    Act Density 0.000%

    No Known Activations