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

    Neuronpedia

    INDEX
    Explanations

    loses value over time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mined
    0.46
     ezingu
    0.43
     vitam
    0.43
     bluntly
    0.42
     domande
    0.41
     stoichiometric
    0.40
    ঠোর
    0.40
    बलेट
    0.40
     laurel
    0.39
    openid
    0.39
    POSITIVE LOGITS
     왜
    0.46
     ہی
    0.43
     neden
    0.43
    现象
    0.43
    创造
    0.42
     없어
    0.42
     когда
    0.40
     때문에
    0.40
     tất
    0.40
    없
    0.40
    Act Density 0.001%

    No Known Activations