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

    Neuronpedia

    INDEX
    Explanations

    Combine publishers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.52
    os
    0.51
     */
    0.48
    </h2>
    0.47
    ::
    0.45
    0.44
     script
    0.44
    ộc
    0.43
    ().
    0.43
     poč
    0.43
    POSITIVE LOGITS
     catalysts
    0.52
     interceptions
    0.51
    垚
    0.50
     imperatives
    0.49
     katal
    0.46
     cataly
    0.45
    حل
    0.44
     deadlines
    0.44
     waging
    0.44
    кмекер
    0.44
    Act Density 0.001%

    No Known Activations