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

    Neuronpedia

    INDEX
    Explanations

    Discussion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .')↵↵
    -0.07
    宝妈
    -0.07
    SelfPermission
    -0.07
     toy
    -0.07
    整整
    -0.07
     Lindsey
    -0.07
    ketøy
    -0.07
     LoginComponent
    -0.07
    ՚
    -0.07
    🥠
    -0.07
    POSITIVE LOGITS
    kir
    0.07
    后悔
    0.07
     exhaust
    0.07
    オス
    0.07
     watering
    0.07
    رس
    0.06
     thất
    0.06
    arriv
    0.06
     Lars
    0.06
    缲
    0.06
    Act Density 0.000%

    No Known Activations