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

    Neuronpedia

    INDEX
    Explanations

    recycling, reuse, or integration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kurs
    0.42
     überprüft
    0.42
    率
    0.42
     RCB
    0.41
     drifts
    0.39
    ifaiFace
    0.38
     Sury
    0.38
    vur
    0.38
     ត
    0.38
    <unused30>
    0.37
    POSITIVE LOGITS
     sống
    0.42
    Living
    0.40
    Gioco
    0.38
     conness
    0.38
     cordless
    0.37
    Ho
    0.37
     ‪
    0.37
     semula
    0.36
    馨
    0.36
     disk
    0.36
    Act Density 0.000%

    No Known Activations