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

    Neuronpedia

    INDEX
    Explanations

    qualifiers for description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BEEN
    1.05
     Agricultura
    1.03
     Educação
    1.00
     Virology
    0.98
    DON
    0.98
    DONT
    0.96
     Vertrieb
    0.96
     neće
    0.94
     BE
    0.93
     DON
    0.91
    POSITIVE LOGITS
    n
    1.05
    lation
    0.88
    apped
    0.86
     for
    0.86
    eworthy
    0.85
     l
    0.82
    aminated
    0.80
    𝑙
    0.79
     oranı
    0.79
    l
    0.79
    Act Density 1.149%

    No Known Activations