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

    Neuronpedia

    INDEX
    Explanations

    business communication phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.98
    یت
    0.73
     an
    0.63
    su
    0.63
    UM
    0.63
    IU
    0.61
    TI
    0.60
    I
    0.60
     An
    0.59
    IT
    0.59
    POSITIVE LOGITS
    ي
    0.92
    توى
    0.84
    ed
    0.78
    ت
    0.76
    ין
    0.74
    عين
    0.74
    تين
    0.72
    י
    0.71
     دين
    0.71
     فريبي
    0.70
    Act Density 0.130%

    No Known Activations