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

    Neuronpedia

    INDEX
    Explanations

    government and corporate secrets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    0.55
    łączy
    0.51
    ل
    0.49
     dlatego
    0.49
     extin
    0.48
    ό
    0.47
    قال
    0.47
     accuses
    0.47
    д
    0.47
    ስታ
    0.46
    POSITIVE LOGITS
     grade
    0.48
    勻
    0.46
     aprovechar
    0.45
    xing
    0.43
     cot
    0.43
     Midi
    0.42
     Superintend
    0.42
    theta
    0.42
     midi
    0.42
     mx
    0.42
    Act Density 0.000%

    No Known Activations