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

    Neuronpedia

    INDEX
    Explanations

    bon / Bon usages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ılarak
    0.42
    执
    0.41
     Definitely
    0.40
    糗
    0.38
    рыв
    0.38
    收费
    0.38
     सूचना
    0.38
    赶紧
    0.37
    ⓗ
    0.37
     unido
    0.37
    POSITIVE LOGITS
     bon
    0.83
    Bon
    0.71
     Bon
    0.70
     BON
    0.69
    bon
    0.66
    anza
    0.63
    bons
    0.61
     marrow
    0.61
     Jovi
    0.60
     bons
    0.58
    Act Density 0.008%

    No Known Activations