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

    Neuronpedia

    INDEX
    Explanations

    open-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CAP
    0.41
    ‌و
    0.37
     etwa
    0.35
    alter
    0.35
    heim
    0.34
    qo
    0.34
    душ
    0.34
    Einstein
    0.34
    ွမ်း
    0.33
    obe
    0.33
    POSITIVE LOGITS
    椂
    0.38
     গণহত্যা
    0.37
     Summer
    0.37
     Sweeney
    0.37
     Ос
    0.36
    unciation
    0.36
     Cherry
    0.36
     Нача
    0.36
    Луч
    0.36
    廰
    0.36
    Act Density 0.007%

    No Known Activations