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

    Neuronpedia

    INDEX
    Explanations

    is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    this
    0.79
    ary
    0.69
    することも
    0.67
    这一点
    0.66
    fig
    0.64
     هذا
    0.63
     এটাও
    0.63
     этом
    0.63
     this
    0.62
    truth
    0.62
    POSITIVE LOGITS
     excerpts
    0.97
     purporting
    0.91
     utilizados
    0.91
     intéressant
    0.90
     utilizzato
    0.88
    allenges
    0.88
     interesting
    0.87
     commemorating
    0.87
     Interesting
    0.86
     দুর্দান্ত
    0.86
    Act Density 0.092%

    No Known Activations