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

    Neuronpedia

    INDEX
    Explanations

    T

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     backyard
    -0.06
    mongoose
    -0.06
    可行性
    -0.06
    房间里
    -0.06
    isor
    -0.06
    �이
    -0.06
    夏日
    -0.06
    酒精
    -0.06
     bringing
    -0.06
    螂
    -0.06
    POSITIVE LOGITS
    _stand
    0.08
    _Mod
    0.08
    $output
    0.07
    (Messages
    0.07
     dossier
    0.07
     Tasks
    0.07
     handset
    0.07
     나타
    0.07
    낚
    0.07
    cosa
    0.07
    Act Density 0.011%

    No Known Activations