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

    Neuronpedia

    INDEX
    Explanations

    pros: introduction of benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    7.65
    ে
    6.53
    t
    6.24
    ০
    6.11
    o
    5.96
    ه
    5.74
    a
    5.71
    ੀ
    5.66
    i
    5.61
    eer
    5.60
    POSITIVE LOGITS
    pośred
    2.88
    に
    2.57
     médic
    2.48
     permeates
    2.41
    𝙔
    2.36
     Tired
    2.28
    ﾝ
    2.26
    ᱾
    2.26
     Перейти
    2.23
    ї
    2.23
    Act Density 0.170%

    No Known Activations