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

    Neuronpedia

    INDEX
    Explanations

    user wants or likes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    頫
    2.65
    璋
    2.40
     р
    2.35
    妃
    2.24
    льку
    2.24
     Watering
    2.22
    జేపీ
    2.19
     Charged
    2.19
     Plough
    2.18
    Farland
    2.17
    POSITIVE LOGITS
    ificantly
    2.48
    ු
    2.32
    y
    2.27
    aesthetic
    2.16
    hk
    2.12
    bibinfo
    2.11
    aturing
    2.09
    ificance
    2.04
    ദ്ധ
    2.00
    びに
    2.00
    Act Density 0.870%

    No Known Activations