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

    Neuronpedia

    INDEX
    Explanations

    builds on existing concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majority
    0.43
     reprinted
    0.40
     majority
    0.39
    majority
    0.39
     Background
    0.39
     Consciousness
    0.38
     Underlying
    0.38
     History
    0.38
     Origin
    0.37
     *}
    0.37
    POSITIVE LOGITS
     themes
    0.65
    themes
    0.59
     темы
    0.55
    concepts
    0.55
     concepts
    0.53
     conceptos
    0.53
    lessons
    0.52
     lessons
    0.50
    years
    0.48
     successes
    0.48
    Act Density 0.030%

    No Known Activations