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

    Neuronpedia

    INDEX
    Explanations

    how are you doing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )],
    0.43
    ood
    0.42
    ⼀
    0.40
     ..............
    0.40
    〇
    0.39
    ‌‌
    0.38
    ​​​​
    0.38
    有好
    0.37
     giải
    0.36
    ]},
    0.36
    POSITIVE LOGITS
    ƴ
    0.45
    ‟
    0.41
    俦
    0.40
     dí
    0.39
    .-\
    0.39
     seventy
    0.38
    vera
    0.38
     môžete
    0.38
    Cur
    0.37
    вин
    0.37
    Act Density 0.004%

    No Known Activations