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

    Neuronpedia

    INDEX
    Explanations

    combining into one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lipid
    0.15
     multif
    0.14
     menghadapi
    0.13
    这边
    0.13
     multiplier
    0.12
     Facing
    0.12
     /$
    0.12
    oyl
    0.12
     Opportunities
    0.12
     Multi
    0.12
    POSITIVE LOGITS
     infantil
    0.15
    ابق
    0.15
     능
    0.15
    含ま
    0.15
    Coords
    0.15
    ﻻ
    0.14
     الخط
    0.14
    ్యా
    0.14
    elace
    0.14
    ្ម
    0.14
    Act Density 0.025%

    No Known Activations