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

    Neuronpedia

    INDEX
    Explanations

    need in a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     múltiples
    0.58
     খুঁজতে
    0.50
    getNum
    0.50
     więcej
    0.50
     时
    0.50
     célèbre
    0.49
     Extraction
    0.49
    icletas
    0.48
     numerosi
    0.48
     bénéficier
    0.47
    POSITIVE LOGITS
    os
    0.45
    า
    0.44
    お
    0.43
     gpd
    0.42
    ts
    0.41
    への
    0.41
    Andre
    0.41
    貢
    0.40
    Centro
    0.40
    <b>
    0.39
    Act Density 0.000%

    No Known Activations