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

    Neuronpedia

    INDEX
    Explanations

    back rub or local fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لی
    0.43
    ⒈
    0.42
     arrivée
    0.40
    bigcap
    0.39
     arrivent
    0.38
     이해
    0.38
     สม
    0.38
     అర్థ
    0.38
    Smooth
    0.38
    𝓊
    0.38
    POSITIVE LOGITS
    watchlist
    0.40
    me
    0.39
     START
    0.37
     AMA
    0.37
     reopened
    0.37
    onbury
    0.37
     dismantled
    0.36
     foreign
    0.36
    mash
    0.36
    esque
    0.35
    Act Density 0.001%

    No Known Activations