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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acept
    -0.06
     todos
    -0.06
    ijn
    -0.06
    sburg
    -0.06
     lidi
    -0.06
     refriger
    -0.06
     kun
    -0.06
    Assembler
    -0.06
    ittest
    -0.06
     önc
    -0.05
    POSITIVE LOGITS
    额
    0.07
    .How
    0.07
     SO
    0.07
    How
    0.07
     solution
    0.07
     Math
    0.07
     motivation
    0.07
     Québec
    0.07
    [args
    0.07
    质量
    0.07
    Act Density 0.082%

    No Known Activations