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

    Neuronpedia

    INDEX
    Explanations

    closing list or object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Judah
    0.40
    ্া
    0.40
    ,?
    0.38
    哪里
    0.37
    ,((
    0.35
    取消
    0.35
    (",",
    0.35
    汞
    0.35
     niacin
    0.34
    問題
    0.34
    POSITIVE LOGITS
    another
    0.42
    finding
    0.40
    lois
    0.39
    Š
    0.38
    notes
    0.37
    üller
    0.37
    λέ
    0.36
    raintes
    0.36
    Another
    0.36
    തന്ത്ര
    0.36
    Act Density 0.052%

    No Known Activations