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

    Neuronpedia

    INDEX
    Explanations

    caption formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     captain
    0.46
     captains
    0.44
     همراه
    0.44
    Captain
    0.41
    accompanied
    0.41
    ត
    0.41
     Captain
    0.40
    堝
    0.39
     accompagné
    0.38
    旄
    0.38
    POSITIVE LOGITS
     Нов
    0.42
    ᕼ
    0.41
     அபி
    0.40
    编译器
    0.38
     "*.
    0.38
     промышлен
    0.38
    ঁচু
    0.38
     %``
    0.38
     Inicio
    0.37
    诞
    0.37
    Act Density 0.000%

    No Known Activations