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

    Neuronpedia

    INDEX
    Explanations

    me or you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ութ
    0.64
     Terbaik
    0.62
    లకు
    0.62
    ajte
    0.61
    േഷൻ
    0.61
     ידי
    0.61
    ﻋ
    0.61
     خ
    0.60
     সাহায্যে
    0.59
    هما
    0.59
    POSITIVE LOGITS
     personally
    1.29
     alone
    1.09
     Personally
    1.02
     pribadi
    1.01
     лично
    0.99
     individually
    0.96
    Personally
    0.96
     persönlich
    0.92
     discounting
    0.88
     personnelle
    0.85
    Act Density 0.066%

    No Known Activations