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

    Neuronpedia

    INDEX
    Explanations

    American

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	filter
    -0.07
     στους
    -0.07
    pedido
    -0.06
    ide
    -0.06
    "That
    -0.06
    IDE
    -0.06
     seaside
    -0.06
    .assertEquals
    -0.06
    庄
    -0.06
     причины
    -0.06
    POSITIVE LOGITS
    awks
    0.06
     evil
    0.06
     renown
    0.06
    .sex
    0.06
    atology
    0.06
     preceding
    0.06
    \Helpers
    0.06
    祥
    0.06
     sanat
    0.06
    ITS
    0.06
    Act Density 0.007%

    No Known Activations