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

    Neuronpedia

    INDEX
    Explanations

    adding information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഉണ്ട
    0.48
     VALLEY
    0.47
     য
    0.45
    Valley
    0.44
    Quiet
    0.44
    Featured
    0.42
     RESER
    0.42
    Cabinet
    0.42
    কাজ
    0.42
    BLE
    0.41
    POSITIVE LOGITS
    سی
    0.56
    zl
    0.51
    رید
    0.50
    zh
    0.48
    ز
    0.46
     canales
    0.46
     pasar
    0.45
    udd
    0.45
    فی
    0.45
    ੱ
    0.45
    Act Density 0.000%

    No Known Activations