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

    Neuronpedia

    INDEX
    Explanations

    cannot / will not phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quilting
    0.40
    提高
    0.39
    However
    0.38
     azonban
    0.37
    Ꮠ
    0.37
     multimeter
    0.36
     допомогою
    0.36
     jednak
    0.35
    改善
    0.35
     However
    0.35
    POSITIVE LOGITS
     cannot
    0.86
     nicht
    0.73
     δεν
    0.73
     není
    0.72
     не
    0.71
    cannot
    0.70
     नहीं
    0.70
     doesn
    0.69
     નથી
    0.67
     didn
    0.66
    Act Density 0.203%

    No Known Activations