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

    Neuronpedia

    INDEX
    Explanations

    Southeast Asia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    curricular
    0.40
     conformal
    0.39
     redirects
    0.38
     settings
    0.38
     सेटिंग
    0.37
     sweetener
    0.37
     asegurarse
    0.37
     fyrir
    0.36
    薊
    0.36
    ాలా
    0.36
    POSITIVE LOGITS
    FFFFFF
    0.42
     Cory
    0.42
    Cory
    0.41
    Autumn
    0.40
     כל
    0.40
    origin
    0.39
    ÁS
    0.39
     origin
    0.38
    つ
    0.38
     polarised
    0.38
    Act Density 0.000%

    No Known Activations