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

    Neuronpedia

    INDEX
    Explanations

    answering common questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h2>
    0.51
     Chiche
    0.47
     to
    0.46
     pake
    0.45
    ன்ன
    0.45
     titolo
    0.45
    Grace
    0.44
    Evaluate
    0.44
    હ
    0.44
     iterate
    0.44
    POSITIVE LOGITS
     история
    0.51
    ıml
    0.50
    읽
    0.44
    taxonomy
    0.44
    浲
    0.44
    camp
    0.43
    рія
    0.43
    valu
    0.43
    푐
    0.43
    储存
    0.43
    Act Density 0.000%

    No Known Activations