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

    Neuronpedia

    INDEX
    Explanations

    []

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    APPLICATION
    -0.08
    安全管理
    -0.08
    web
    -0.08
    Super
    -0.08
     technique
    -0.08
     Spatial
    -0.08
    指挥
    -0.07
    gd
    -0.07
    对手
    -0.07
    controls
    -0.07
    POSITIVE LOGITS
     [],
    0.07
     새로
    0.07
     diversas
    0.07
    んな
    0.07
    /Observable
    0.07
     Ма
    0.07
    たくさん
    0.07
    manın
    0.07
     ([]
    0.07
    =[],
    0.07
    Act Density 0.008%

    No Known Activations