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

    Neuronpedia

    INDEX
    Explanations

    boot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _plugins
    -0.08
     сторон
    -0.07
    וך
    -0.07
     hence
    -0.07
    Plugins
    -0.07
    arnas
    -0.07
     แ
    -0.07
    Debugger
    -0.07
    veloped
    -0.07
    ープ
    -0.07
    POSITIVE LOGITS
     subdivisions
    0.08
    २४
    0.08
     pà
    0.08
     encrypt
    0.08
     температуры
    0.08
     клетки
    0.08
     {}
    0.08
     wing
    0.07
     escrit
    0.07
     zware
    0.07
    Act Density 0.001%

    No Known Activations