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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Appropri
    -0.07
    Successfully
    -0.07
    Dict
    -0.07
    ][
    -0.07
     수상
    -0.07
     economic
    -0.06
    _LINES
    -0.06
     unaware
    -0.06
    struction
    -0.06
     Specialist
    -0.06
    POSITIVE LOGITS
    jual
    0.07
    预览
    0.06
     Naj
    0.06
    Endian
    0.06
     defenseman
    0.06
     oath
    0.06
     นาย
    0.06
    -prepend
    0.06
    _makeConstraints
    0.06
     Voj
    0.06
    Act Density 0.006%

    No Known Activations