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

    Neuronpedia

    INDEX
    Explanations

    explaining an assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    T
    0.43
    ，
    0.43
    升
    0.42
    DH
    0.41
    D
    0.41
    盛
    0.40
     Cy
    0.40
    Lift
    0.40
    陶
    0.40
     Thrift
    0.39
    POSITIVE LOGITS
    𝘯
    0.51
    いが
    0.50
    mprj
    0.49
     सर्वात
    0.49
     އަ
    0.49
     Бүген
    0.48
     !")
    0.48
     नोट्स
    0.48
    addAnimation
    0.48
    𝗻
    0.47
    Act Density 0.002%

    No Known Activations