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

    Neuronpedia

    INDEX
    Explanations

    base foundation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ди
    1.14
    v
    1.09
    j
    1.09
    ар
    1.06
    ین
    1.05
    きた
    1.01
    ю
    0.98
    لي
    0.96
    я
    0.94
    t
    0.93
    POSITIVE LOGITS
     for
    1.55
     Base
    1.52
     base
    1.27
    es
    1.23
     BASE
    1.21
    are
    1.12
    año
    1.11
     आधार
    1.09
     dasar
    1.09
    he
    1.09
    Act Density 0.235%

    No Known Activations