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

    Neuronpedia

    INDEX
    Explanations

    following usual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ो
    1.32
    ی
    1.30
    ো
    1.28
    ా
    1.24
    ться
    1.20
    িশালী
    1.17
    م
    1.16
     armoured
    1.16
     armored
    1.12
    া
    1.12
    POSITIVE LOGITS
    .
    1.40
     vzd
    1.34
     luta
    1.33
     dificult
    1.32
     acompañado
    1.32
     આન
    1.31
    BEN
    1.30
     suspects
    1.28
    IO
    1.27
    umum
    1.27
    Act Density 0.032%

    No Known Activations