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

    Neuronpedia

    INDEX
    Explanations

    taxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AN
    0.55
    ES
    0.46
     ujar
    0.45
    ASA
    0.44
    ER
    0.43
    IA
    0.42
    AT
    0.41
    ch
    0.40
    AC
    0.40
    0
    0.40
    POSITIVE LOGITS
    сти
    0.59
    nilai
    0.54
    ล
    0.52
    ا
    0.50
    です
    0.49
    asının
    0.48
    да
    0.48
    とても
    0.47
    🏥
    0.47
     சிகி
    0.47
    Act Density 1.159%

    No Known Activations