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

    Neuronpedia

    INDEX
    Explanations

    attachment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     говорит
    -0.07
    鹅
    -0.07
    “For
    -0.07
     страны
    -0.06
    Jesus
    -0.06
     But
    -0.06
    꺠
    -0.06
    Mis
    -0.06
    .AddComponent
    -0.06
     unfolds
    -0.06
    POSITIVE LOGITS
    ffffff
    0.08
     prio
    0.07
     shipping
    0.07
    _low
    0.07
    抢抓
    0.07
     );↵
    0.07
     plasma
    0.07
    almö
    0.07
     displayName
    0.07
    퓮
    0.07
    Act Density 0.004%

    No Known Activations