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

    Neuronpedia

    INDEX
    Explanations

    universe events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    1.67
    י
    1.43
    ları
    1.34
    ين
    1.32
    liği
    1.26
    م
    1.21
    ം
    1.21
    izes
    1.17
     remod
    1.17
    ೦
    1.17
    POSITIVE LOGITS
    IM
    1.26
    contributors
    1.24
    enquête
    1.16
    ש
    1.16
    內的
    1.16
    يها
    1.14
    pipelines
    1.14
     possèdent
    1.14
    caches
    1.13
    commits
    1.13
    Act Density 0.095%

    No Known Activations