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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elapsed
    -0.07
    rogate
    -0.07
     treaty
    -0.07
     tersebut
    -0.06
    �
    -0.06
    rado
    -0.06
     Razor
    -0.06
     Pandora
    -0.06
    THOOK
    -0.06
     uploaded
    -0.06
    POSITIVE LOGITS
    _SHAPE
    0.07
    �
    0.06
     BOARD
    0.06
    を見る
    0.06
    belief
    0.06
    UTIL
    0.06
    ="<<
    0.06
    .getIndex
    0.06
     větš
    0.06
     продукты
    0.06
    Act Density 0.021%

    No Known Activations