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

    Neuronpedia

    INDEX
    Explanations

    sleep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ви
    1.59
    ро
    1.55
     aerosols
    1.55
     conifers
    1.52
     interspersed
    1.50
    ках
    1.49
     subsidiaries
    1.49
     sulfides
    1.48
     conglomerates
    1.45
     carcinomas
    1.45
    POSITIVE LOGITS
    اد
    1.64
    م
    1.64
    𓇼
    1.63
    istán
    1.61
    لي
    1.55
    rights
    1.55
    💤
    1.54
    end
    1.53
     également
    1.53
    اه
    1.52
    Act Density 0.016%

    No Known Activations