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

    Neuronpedia

    INDEX
    Explanations

    include some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     và
    0.76
     және
    0.74
     и
    0.73
     agus
    0.73
     आणि
    0.71
    不仅
    0.71
     and
    0.69
     both
    0.68
     এবং
    0.68
     અને
    0.68
    POSITIVE LOGITS
     ಇತರ
    0.93
     अन्य
    0.91
    其他的
    0.90
     અન્ય
    0.87
     outras
    0.82
     другие
    0.78
     otros
    0.78
     других
    0.75
    其他
    0.75
    的其他
    0.74
    Act Density 0.354%

    No Known Activations