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

    Neuronpedia

    INDEX
    Explanations

    Sultanate, Difference, child

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tat
    0.44
     artériel
    0.42
     TAT
    0.42
     exoner
    0.41
    বাবুর
    0.41
     renderEncoder
    0.41
    gård
    0.40
    ••
    0.39
    ujukan
    0.39
     unattainable
    0.39
    POSITIVE LOGITS
    رض
    0.46
    ↵
    0.46
    phe
    0.45
     normaal
    0.44
     normal
    0.43
     Come
    0.42
    عب
    0.42
    пре
    0.41
    come
    0.41
    Voting
    0.41
    Act Density 0.000%

    No Known Activations