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

    Neuronpedia

    INDEX
    Explanations

    compliance plugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不必
    0.50
    Xpaths
    0.43
     আশে
    0.43
     colds
    0.41
    ridos
    0.41
    parsing
    0.41
     attendre
    0.41
    Ideally
    0.41
     必要
    0.40
     viajes
    0.39
    POSITIVE LOGITS
     talented
    0.53
     volunteer
    0.47
     liaison
    0.44
     SAB
    0.43
     representative
    0.42
     Malaysian
    0.42
     premier
    0.42
     representa
    0.42
     NAB
    0.41
     Pul
    0.41
    Act Density 0.001%

    No Known Activations