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

    Neuronpedia

    INDEX
    Explanations

    reporting speech and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cosidd
    0.52
     sogenannte
    0.52
     tzw
    0.51
     socalled
    0.50
     sogen
    0.49
    所谓的
    0.47
    所谓
    0.46
     sogenannten
    0.45
     tzv
    0.43
    所謂
    0.42
    POSITIVE LOGITS
     "...
    1.06
     "..
    0.96
     "¿
    0.92
    "...
    0.90
     “…
    0.88
     :"
    0.84
     "[
    0.82
     *"
    0.81
    _"
    0.80
    :"
    0.79
    Act Density 0.286%

    No Known Activations