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

    Neuronpedia

    INDEX
    Explanations

    numbers and letters following 't'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ဗ
    0.56
    酈
    0.51
    ラ
    0.46
    稣
    0.45
     aboard
    0.45
    বৃহ
    0.45
    ার্জি
    0.45
     productos
    0.44
    ライン
    0.44
    гает
    0.44
    POSITIVE LOGITS
    dimethyl
    0.46
    ény
    0.44
    ng
    0.43
    وم
    0.43
     схема
    0.43
     aswell
    0.42
     консу
    0.42
    ussa
    0.41
     Scheme
    0.41
    ją
    0.41
    Act Density 0.109%

    No Known Activations