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

    Neuronpedia

    INDEX
    Explanations

    python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demonstrating
    0.41
    En
    0.41
    yg
    0.38
    λλη
    0.38
    ounding
    0.38
     Segment
    0.37
    When
    0.36
     Initially
    0.36
    ానిక
    0.36
    ↵
    0.36
    POSITIVE LOGITS
    TreeNavigator
    0.42
     Shaq
    0.41
     handleSubmit
    0.39
     tanı
    0.38
    犸
    0.38
    ableConcept
    0.38
     sacraments
    0.37
    SleepHours
    0.37
    AndUpdate
    0.37
     ]);
    0.36
    Act Density 0.038%

    No Known Activations