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

    Neuronpedia

    INDEX
    Explanations

    B2B, E2EE, NAFLD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    те
    1.28
     poet
    1.09
    的时间
    1.01
    );
    1.00
    вает
    0.98
    했으며
    0.96
     dona
    0.96
    ৯
    0.96
     hath
    0.95
    로운
    0.95
    POSITIVE LOGITS
    و
    1.50
    e
    1.41
    nr
    1.34
    eing
    1.29
    lere
    1.29
    u
    1.28
    lardan
    1.27
    larda
    1.26
    l
    1.25
    t
    1.24
    Act Density 0.111%

    No Known Activations