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

    Neuronpedia

    INDEX
    Explanations

    suggestions, criteria, placement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Update
    0.53
    绝
    0.46
    信息
    0.42
    解读
    0.42
    目录
    0.42
    Update
    0.42
     Spread
    0.42
     Updates
    0.41
    ডে
    0.41
     Danger
    0.40
    POSITIVE LOGITS
    ião
    0.47
     inks
    0.47
    üp
    0.46
     бюд
    0.45
    eské
    0.45
     lubricants
    0.44
    ᠴ
    0.42
    astres
    0.42
    ⵡ
    0.42
    lige
    0.41
    Act Density 0.007%

    No Known Activations