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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BLOCK
    -0.07
     furniture
    -0.07
     Command
    -0.07
    '.↵↵
    -0.07
     boxes
    -0.07
     block
    -0.07
     techn
    -0.06
     Block
    -0.06
     Cham
    -0.06
     nachází
    -0.06
    POSITIVE LOGITS
    ẩn
    0.07
     airlines
    0.07
    айте
    0.07
    nez
    0.07
    multiply
    0.06
     Agile
    0.06
    INIT
    0.06
     reliable
    0.06
     turbine
    0.06
     airline
    0.06
    Act Density 0.003%

    No Known Activations