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

    Neuronpedia

    INDEX
    Explanations

    care and concern for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cailles
    2.52
    涳
    2.38
    muc
    2.36
     sawdust
    2.34
     tablespoon
    2.31
    eran
    2.26
     habido
    2.26
    कारात्मक
    2.26
    ी
    2.25
    蛎
    2.25
    POSITIVE LOGITS
     사항
    2.79
    รักษา
    2.58
    AspectRatio
    2.29
    忡
    2.27
    giver
    2.23
    givers
    2.13
     dnia
    2.07
    ittle
    2.07
    roidism
    2.04
     attuned
    2.03
    Act Density 0.167%

    No Known Activations