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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     六
    -0.07
    former
    -0.06
    ονται
    -0.06
    .Assert
    -0.06
    Backing
    -0.06
    -seat
    -0.06
    pleasant
    -0.06
    .*;
↵
↵
    -0.06
     undo
    -0.06
    mitter
    -0.06
    POSITIVE LOGITS
    	UN
    0.07
     căn
    0.06
     fotos
    0.06
     Stafford
    0.06
    	error
    0.06
     Bison
    0.06
    *u
    0.06
    _ANT
    0.06
    _KEY
    0.06
    «
    0.06
    Act Density 0.002%

    No Known Activations