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

    Neuronpedia

    INDEX
    Explanations

    rules and restrictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ాబ
    -0.09
     Pfer
    -0.08
     raster
    -0.07
     helicopter
    -0.07
    ことで
    -0.07
     uncomment
    -0.07
     знач
    -0.07
    .cell
    -0.07
     విల
    -0.07
     Gunn
    -0.07
    POSITIVE LOGITS
     conspir
    0.08
     convencer
    0.08
     сопровож
    0.08
    brief
    0.08
    sheng
    0.08
    偷偷
    0.08
     сопров
    0.08
     ensl
    0.08
    /conf
    0.08
    骗人
    0.08
    Act Density 0.001%

    No Known Activations