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
     négociations
    -0.56
     attentes
    -0.50
    itinéraire
    -0.49
     bénéfices
    -0.49
     preuves
    -0.48
     connaissances
    -0.48
     goûts
    -0.47
     säl
    -0.47
     travailleurs
    -0.46
     débats
    -0.46
    POSITIVE LOGITS
    makeConstraints
    0.75
     segments
    0.72
     panes
    0.69
     cycles
    0.67
     notches
    0.66
     createState
    0.65
     cubes
    0.64
     perfons
    0.64
     panels
    0.64
     domes
    0.63
    Act Density 0.006%

    No Known Activations