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

    Neuronpedia

    INDEX
    Explanations

    path led to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.21
    ي
    1.09
    g
    1.05
    de
    1.01
    i
    1.00
    ни
    1.00
    ni
    0.96
    th
    0.94
    ag
    0.93
    na
    0.93
    POSITIVE LOGITS
    」。
    0.93
     powied
    0.91
    ↵↵↵
    0.83
    </h3>
    0.83
    னர்
    0.82
    이었
    0.82
     delirium
    0.80
     financeira
    0.80
     concili
    0.80
    ↵↵
    0.79
    Act Density 0.007%

    No Known Activations