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

    Neuronpedia

    INDEX
    Explanations

    Therefore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ID
    -0.07
    )prepare
    -0.07
     appended
    -0.07
    /common
    -0.06
    withdraw
    -0.06
    _outline
    -0.06
    virtual
    -0.06
    -place
    -0.06
     inventions
    -0.06
     centralized
    -0.06
    POSITIVE LOGITS
     gấp
    0.07
     условиях
    0.06
     somebody
    0.06
     namoro
    0.06
     پرونده
    0.06
    igu
    0.06
    啪
    0.06
    .MapFrom
    0.06
    менту
    0.06
    omu
    0.06
    Act Density 0.024%

    No Known Activations