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

    Neuronpedia

    INDEX
    Explanations

    Code, programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dí
    -0.07
     CreateTable
    -0.07
    iers
    -0.07
    拉萨
    -0.06
     instances
    -0.06
     publi
    -0.06
    وبا
    -0.06
    无助
    -0.06
     clearing
    -0.06
     Pane
    -0.06
    POSITIVE LOGITS
     predictable
    0.08
    Session
    0.07
    就是要
    0.07
     zupeł
    0.07
    ほぼ
    0.07
     geldiği
    0.07
    ENABLE
    0.07
    鐾
    0.07
    getBlock
    0.07
     duy
    0.07
    Act Density 0.083%

    No Known Activations