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

    Neuronpedia

    INDEX
    Explanations

    technical terms multilingually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     format
    0.41
    overleftarrow
    0.38
     FORMAT
    0.37
     MDLVertex
    0.37
    蜀
    0.37
     PNG
    0.37
     生命周期函数
    0.37
    格式
    0.36
    και
    0.36
     כול
    0.36
    POSITIVE LOGITS
     энцикло
    0.42
    EnumValue
    0.40
    UserInfo
    0.39
    vetica
    0.39
    未知
    0.39
     سطح
    0.39
    UserRepository
    0.39
     livello
    0.39
     قدیمی
    0.39
    Undefined
    0.38
    Act Density 0.000%

    No Known Activations