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

    Neuronpedia

    INDEX
    Explanations

    if not already

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িদের
    0.46
    essor
    0.45
    </h2>
    0.44
    必需
    0.43
    ON
    0.41
     said
    0.41
    name
    0.41
    ઓની
    0.41
     đừng
    0.41
    factory
    0.40
    POSITIVE LOGITS
     значительно
    0.44
    ذية
    0.43
    Antaeotricha
    0.42
    Brien
    0.41
    浿
    0.41
     bereits
    0.41
    nave
    0.41
    сшта
    0.41
    浻
    0.40
    परेट
    0.40
    Act Density 0.005%

    No Known Activations