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

    Neuronpedia

    INDEX
    Explanations

    bounding boxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    せます
    -0.74
     background
    -0.73
     Lans
    -0.73
    datepicker
    -0.71
    ക്ക്
    -0.70
    books
    -0.70
    슘
    -0.67
    ardi
    -0.66
    начала
    -0.66
    amination
    -0.65
    POSITIVE LOGITS
     bounding
    1.84
     box
    1.77
     boxes
    1.66
     bbox
    1.52
    Box
    1.48
    boxes
    1.47
     Boxes
    1.44
    box
    1.40
    Boxes
    1.37
     Box
    1.36
    Act Density 0.034%

    No Known Activations