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

    Neuronpedia

    INDEX
    Explanations

    unit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piece
    -0.07
     Piece
    -0.07
    -Cds
    -0.07
     Ide
    -0.07
     Learn
    -0.06
     Jeremiah
    -0.06
    เลข
    -0.06
    >H
    -0.06
    elts
    -0.06
    Edges
    -0.06
    POSITIVE LOGITS
     sque
    0.06
    .PO
    0.06
     Marcos
    0.06
     duties
    0.06
    getSession
    0.06
     scrut
    0.06
     Detail
    0.06
    spNet
    0.06
    	names
    0.06
    .stack
    0.06
    Act Density 0.003%

    No Known Activations