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

    Neuronpedia

    INDEX
    Explanations

    seamless pipes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étaient
    1.09
     était
    0.96
     seront
    0.95
    origines
    0.95
    upport
    0.89
     singularly
    0.87
    ار
    0.87
     é
    0.87
     precedenti
    0.86
     avait
    0.85
    POSITIVE LOGITS
    掌控
    1.06
     Encode
    0.96
     Membuat
    0.93
     kişinin
    0.93
     Containing
    0.91
     menjaga
    0.91
     Nasıl
    0.91
     Halls
    0.90
    ត្រូវការ
    0.88
     Dealing
    0.88
    Act Density 0.000%

    No Known Activations