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

    Neuronpedia

    INDEX
    Explanations

    python code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.51
    (
    0.50
    ara
    0.48
    ;
    0.42
     కానీ
    0.42
     atthe
    0.41
     (=
    0.41
     entsprechend
    0.41
    ainkan
    0.40
    ，
    0.40
    POSITIVE LOGITS
    ポ
    0.52
    ли
    0.50
    ری
    0.50
    и
    0.49
    он
    0.47
    у
    0.46
    カ
    0.46
    𝘀
    0.46
    о
    0.46
    ка
    0.46
    Act Density 1.024%

    No Known Activations