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

    Neuronpedia

    INDEX
    Explanations

    be a safe and helpful AI assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    word
    0.34
     mindful
    0.34
    commonly
    0.34
     wooded
    0.33
    reasonable
    0.33
    uminescent
    0.33
    unsaturated
    0.32
    featur
    0.32
     coniferous
    0.32
    urgent
    0.32
    POSITIVE LOGITS
     একজন
    0.57
    一名
    0.41
     finishes
    0.38
     seorang
    0.38
     Reports
    0.36
     Rates
    0.36
     molestias
    0.36
     an
    0.36
     Compliance
    0.36
     déplacements
    0.36
    Act Density 0.011%

    No Known Activations