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

    Neuronpedia

    INDEX
    Explanations

    clothing items, tips, lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    removal
    0.55
    Delivery
    0.54
    Concurrency
    0.52
    ់
    0.50
     დაბ
    0.49
    impurity
    0.49
    Decoding
    0.48
    maximal
    0.48
    ುತ್ತೇವೆ
    0.48
    smtp
    0.46
    POSITIVE LOGITS
    .
    0.47
     jó
    0.46
     dalam
    0.46
     tribute
    0.44
    的孩子
    0.44
     rup
    0.42
     beat
    0.42
     nouveau
    0.41
     nei
    0.41
     Hakk
    0.41
    Act Density 0.001%

    No Known Activations