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

    Neuronpedia

    INDEX
    Explanations

    many stakeholders or teenagers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iation
    0.42
    ו
    0.42
    পথ
    0.40
     "_"
    0.39
     τι
    0.39
     primitives
    0.39
    εν
    0.37
    ^*_{
    0.37
    ه‌ها
    0.37
    ర్
    0.37
    POSITIVE LOGITS
     einem
    0.48
    ieważ
    0.46
     outboard
    0.43
    tten
    0.41
     einer
    0.41
    луйста
    0.41
    quisitos
    0.40
     einige
    0.40
     been
    0.39
     kasus
    0.39
    Act Density 0.005%

    No Known Activations