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

    Neuronpedia

    INDEX
    Explanations

    deepest expressions of empathy or desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.66
    t
    1.59
    re
    1.57
    u
    1.53
    m
    1.52
     as
    1.40
    r
    1.38
    ม
    1.36
    a
    1.35
    te
    1.34
    POSITIVE LOGITS
    čním
    1.06
    вающие
    0.99
    டு
    0.96
    ků
    0.96
    ếu
    0.93
    вающая
    0.93
    闓
    0.93
    cessing
    0.91
    ך
    0.91
    κή
    0.90
    Act Density 0.000%

    No Known Activations