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

    Neuronpedia

    INDEX
    Explanations

    which introduces a clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whatnot
    0.93
     Nowhere
    0.84
     None
    0.83
    করণ
    0.82
    })-\
    0.80
    BottomOf
    0.80
     cât
    0.80
     wanting
    0.79
     Irina
    0.79
     அனை
    0.77
    POSITIVE LOGITS
    يد
    1.02
     позволя
    0.93
     provides
    0.91
     কিনা
    0.91
     allows
    0.90
     establishes
    0.88
     lequel
    0.86
     minimizes
    0.86
     обеспечивает
    0.85
     представляет
    0.85
    Act Density 0.001%

    No Known Activations