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

    Neuronpedia

    INDEX
    Explanations

    foundational or essential concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.29
     Pear
    0.28
    <b>
    0.28
     the
    0.28
     \
    0.28
     Dr
    0.27
    \
    0.27
     Z
    0.26
     corresponding
    0.26
     DR
    0.26
    POSITIVE LOGITS
    式的
    0.32
    वें
    0.32
    ப்படுத்தி
    0.31
    的な
    0.31
    적인
    0.31
     situazioni
    0.30
     hráč
    0.30
    之地
    0.30
     রকমের
    0.29
    般的
    0.29
    Act Density 0.151%

    No Known Activations