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

    Neuronpedia

    INDEX
    Explanations

    math notation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     –
    0.40
    ՝
    0.39
    ⇧
    0.38
    лое
    0.38
    রার
    0.37
    \}$.
    0.36
     `;
    0.36
    ')).
    0.35
    BUF
    0.35
    Sup
    0.35
    POSITIVE LOGITS
    }_{
    0.50
    =_
    0.42
     $_{
    0.38
     pare
    0.38
     بهتر
    0.37
    $_{
    0.36
    തേ
    0.36
    )}_{
    0.35
    }_
    0.35
     mejor
    0.35
    Act Density 0.001%

    No Known Activations