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

    Neuronpedia

    INDEX
    Explanations

    TODAY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rag
    0.41
     Rag
    0.40
     rag
    0.40
    ycji
    0.39
     leach
    0.38
    0.38
     Яро
    0.38
     tyrann
    0.37
    yczy
    0.36
    IQ
    0.36
    POSITIVE LOGITS
    ay
    1.70
    AY
    1.50
    ays
    1.49
     ay
    1.47
    AYS
    1.29
    Ay
    1.22
     AY
    1.22
     Ay
    1.19
    اي
    1.15
    aying
    1.09
    Act Density 0.004%

    No Known Activations