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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    álás
    0.86
    FromArgb
    0.75
    shoz
    0.70
    ात
    0.65
    볐
    0.63
    લમાં
    0.62
    કમાં
    0.62
     ውስጥ
    0.62
    ᓕ
    0.61
    ränkt
    0.61
    POSITIVE LOGITS
     on
    5.79
     trên
    4.12
     على
    4.00
     på
    3.99
    บน
    3.79
     на
    3.73
     On
    3.62
     pada
    3.54
    On
    3.48
     บน
    3.48
    Act Density 2.039%

    No Known Activations