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

    Neuronpedia

    INDEX
    Explanations

    during communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    published
    0.49
     都市
    0.47
    CRT
    0.46
    CR
    0.46
     개발
    0.44
    ជីវ
    0.44
     ciudadanos
    0.44
    COMPAR
    0.44
     வரலாற்று
    0.43
    ˆ‚
    0.43
    POSITIVE LOGITS
     spectators
    0.64
     tijdens
    0.58
     instructor
    0.54
     podczas
    0.54
     أثناء
    0.54
     během
    0.54
     durante
    0.53
     sırasında
    0.52
     Observing
    0.52
     during
    0.52
    Act Density 0.118%

    No Known Activations