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

    Neuronpedia

    INDEX
    Explanations

    reboot, disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    2.22
    t
    2.13
    可以
    2.11
    ian
    2.06
    有序
    2.05
    ۱
    2.05
    说
    2.00
    ۹
    2.00
    ang
    1.98
    م
    1.98
    POSITIVE LOGITS
    ้
    1.91
     marts
    1.75
     automóviles
    1.69
     reactors
    1.65
    ból
    1.57
     alumnos
    1.53
    oooo
    1.52
     рынка
    1.52
    но
    1.48
    특별시
    1.48
    Act Density 0.282%

    No Known Activations