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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ResourceType
    -0.07
    中に
    -0.06
     من
    -0.06
     resides
    -0.06
    Merc
    -0.06
    传奇里面
    -0.06
    .isArray
    -0.06
    .localPosition
    -0.06
     Wiley
    -0.06
     nb
    -0.06
    POSITIVE LOGITS
    亮眼
    0.08
    _ma
    0.07
     Teil
    0.07
     STM
    0.07
    手掌
    0.07
    _SCALE
    0.07
    *ft
    0.07
     Yii
    0.07
    执勤
    0.07
    𝓕
    0.07
    Act Density 0.009%

    No Known Activations