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

    Neuronpedia

    INDEX
    Explanations

    math.pow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cogeneration
    0.40
    মূলক
    0.40
    Objet
    0.38
    开始了
    0.38
     warrantless
    0.37
     awe
    0.37
     quantifying
    0.37
    Codec
    0.37
     isomerization
    0.37
     scholarly
    0.36
    POSITIVE LOGITS
    га
    0.43
    กับ
    0.39
    ान
    0.37
    बंद
    0.37
    with
    0.37
    ાઈ
    0.36
    )}^{
    0.36
     with
    0.35
     blockers
    0.35
    delen
    0.35
    Act Density 0.000%

    No Known Activations