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

    Neuronpedia

    INDEX
    Explanations

    book titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্ধ
    0.41
     ஆ
    0.41
    \:
    0.40
     collectives
    0.40
     Democracy
    0.38
     धारणा
    0.38
     imposition
    0.37
    දය
    0.37
     обяза
    0.37
     Colour
    0.37
    POSITIVE LOGITS
    Gregor
    0.49
     Esperanza
    0.46
     Ranger
    0.46
     Holes
    0.46
    Louis
    0.46
    Charlotte
    0.44
    Ella
    0.43
    Joey
    0.43
     Ella
    0.43
    Pax
    0.42
    Act Density 0.004%

    No Known Activations