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

    Neuronpedia

    INDEX
    Explanations

    scheduling algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     integrante
    0.96
    かん
    0.95
    nextToken
    0.94
    стоя
    0.92
    𝑦
    0.90
    anny
    0.90
     पाइ
    0.87
     титу
    0.87
    스크
    0.86
    ้
    0.86
    POSITIVE LOGITS
    बद्ध
    1.18
    pflege
    1.18
     ticking
    1.08
     uptime
    1.07
    ūra
    1.06
     pubescens
    1.06
    icity
    1.06
    ulers
    1.04
    安排
    1.04
     derail
    1.03
    Act Density 0.076%

    No Known Activations