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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     applaud
    -0.07
     ensures
    -0.07
    Latch
    -0.07
     의원
    -0.07
    Cy
    -0.07
    プレゼント
    -0.07
     지원
    -0.07
     contribute
    -0.07
     clot
    -0.07
    PIN
    -0.07
    POSITIVE LOGITS
    osex
    0.07
    ymology
    0.07
    🔀
    0.07
    _feat
    0.07
    mouseup
    0.07
     gover
    0.07
    🎮
    0.07
    controllers
    0.07
     curses
    0.07
    豕
    0.07
    Act Density 0.021%

    No Known Activations