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

    Neuronpedia

    INDEX
    Explanations

    points of interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ​​
    1.53
    ar
    1.41
    दर्शी
    1.38
    𝒽
    1.37
    р
    1.35
    𝚑
    1.29
    ﻁ
    1.29
    ﻅ
    1.29
    nå
    1.27
     dichiarato
    1.25
    POSITIVE LOGITS
    ات
    1.96
    s
    1.87
    ्स
    1.60
    polo
    1.48
    sü
    1.47
    ς
    1.47
    ੀ
    1.46
    sd
    1.45
    todo
    1.43
    south
    1.40
    Act Density 0.001%

    No Known Activations