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

    Neuronpedia

    INDEX
    Explanations

    wind chimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    0.52
    G
    0.48
     پ
    0.48
    েশ্বর
    0.46
    D
    0.46
    t
    0.46
    N
    0.45
    C
    0.45
    AN
    0.45
    matory
    0.44
    POSITIVE LOGITS
     inglesa
    0.57
    ügel
    0.52
    cuando
    0.51
     όταν
    0.50
     griega
    0.50
     suç
    0.49
     kucch
    0.48
    ̣ng
    0.47
    çok
    0.47
     όχι
    0.47
    Act Density 0.000%

    No Known Activations