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

    Neuronpedia

    INDEX
    Explanations

    torque

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     echar
    1.27
    ्न
    1.24
     introd
    1.24
     indígena
    1.24
    fills
    1.23
    iveness
    1.20
     mea
    1.20
    বন্ত
    1.20
    okkal
    1.20
     fontweight
    1.19
    POSITIVE LOGITS
    不斷
    1.34
    μές
    1.31
    赉
    1.27
    Xi
    1.24
    ຶ
    1.20
    LE
    1.19
    REET
    1.17
     Особенно
    1.13
    AL
    1.11
    ۴
    1.11
    Act Density 0.003%

    No Known Activations