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

    Neuronpedia

    INDEX
    Explanations

    spy, turnover, feeling, crop, yogurt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     closing
    0.39
    ological
    0.38
     scouring
    0.36
    closing
    0.36
    ο
    0.36
    alo
    0.35
    assen
    0.34
    orting
    0.34
    <0x97>
    0.34
    urrent
    0.34
    POSITIVE LOGITS
     partecipanti
    0.39
    育て
    0.37
     sauber
    0.37
     mystery
    0.36
    神秘
    0.36
    Kelas
    0.36
    DVRIP
    0.36
     Sapir
    0.35
     baseApiPath
    0.35
    सदीय
    0.35
    Act Density 0.001%

    No Known Activations