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

    Neuronpedia

    INDEX
    Explanations

    diversity and versatility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tahap
    1.07
     verrou
    0.93
    影响
    0.88
     dépl
    0.85
     kanya
    0.81
    autres
    0.81
    تبر
    0.80
     pergi
    0.80
     sareng
    0.80
    看来
    0.79
    POSITIVE LOGITS
    c
    1.15
    d
    1.03
    y
    1.02
    ли
    1.01
    ي
    0.98
    ни
    0.95
    al
    0.94
    та
    0.87
     Algorithms
    0.86
    th
    0.84
    Act Density 0.110%

    No Known Activations