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

    Neuronpedia

    INDEX
    Explanations

    My guardrails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    airie
    0.43
    OID
    0.39
     تشتغل
    0.39
    કરી
    0.37
    GUI
    0.37
    跇
    0.37
    वाहिक
    0.36
    袋
    0.36
    Ｕ
    0.36
    烦
    0.36
    POSITIVE LOGITS
     Bronson
    0.42
     belirli
    0.39
     civilizations
    0.38
     親
    0.38
     Pythagorean
    0.38
     LeBron
    0.37
    franch
    0.37
     கமல்ஹா
    0.37
     Nail
    0.37
     influ
    0.36
    Act Density 0.000%

    No Known Activations