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

    Neuronpedia

    INDEX
    Explanations

    cannot and will not fulfill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.59
    et
    1.58
    ü
    1.34
    d
    1.29
    g
    1.29
    ed
    1.24
    b
    1.18
    au
    1.16
    ill
    1.16
    c
    1.14
    POSITIVE LOGITS
    the
    1.27
    ’
    0.90
     fulfill
    0.80
    0.78
     fulfilled
    0.77
    </h2>
    0.77
    ின்
    0.77
     burdensome
    0.75
    יה
    0.74
    ுங்கள்
    0.73
    Act Density 0.014%

    No Known Activations