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

    Neuronpedia

    INDEX
    Explanations

    NSMutableArray

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getSource
    -0.07
     awake
    -0.07
     không
    -0.06
    .listdir
    -0.06
     Див
    -0.06
    ServiceImpl
    -0.06
    List
    -0.06
    退出
    -0.06
    .JLabel
    -0.06
     وجه
    -0.06
    POSITIVE LOGITS
     COMM
    0.07
    ryan
    0.07
     appealing
    0.07
    decl
    0.07
     cane
    0.07
    عل
    0.07
    "github
    0.06
    لف
    0.06
    REEN
    0.06
    ุบ
    0.06
    Act Density 0.003%

    No Known Activations