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

    Neuronpedia

    INDEX
    Explanations

    code and data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ジャパン
    0.45
     sabbam
    0.42
    GALAD
    0.42
     AppBsky
    0.41
    DAAR
    0.41
    🫡
    0.41
    스가
    0.41
    ແລະ
    0.41
    스와
    0.41
    τιο
    0.40
    POSITIVE LOGITS
     on
    0.67
    il
    0.58
    ne
    0.57
     in
    0.55
     is
    0.55
    ة
    0.54
     has
    0.53
    en
    0.52
    in
    0.52
     can
    0.51
    Act Density 0.284%

    No Known Activations