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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ДЕ
    -0.08
     Isles
    -0.08
    uele
    -0.08
    翛
    -0.08
    ✿
    -0.07
    슬
    -0.07
    迟迟
    -0.07
    izarre
    -0.07
     viene
    -0.07
    achie
    -0.07
    POSITIVE LOGITS
    破坏
    0.08
    关闭
    0.08
     interpolation
    0.08
     loading
    0.08
     wash
    0.07
     automated
    0.07
     localization
    0.07
     control
    0.07
     Control
    0.07
     reset
    0.07
    Act Density 0.001%

    No Known Activations