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

    Neuronpedia

    INDEX
    Explanations

    drawing commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Size
    0.80
    size
    0.80
    Info
    0.73
     sidd
    0.70
    SIZE
    0.69
     Size
    0.67
     size
    0.66
    GFP
    0.66
    info
    0.65
    Name
    0.65
    POSITIVE LOGITS
     pé
    0.76
     Pact
    0.75
     आरओ
    0.74
     wk
    0.71
     arc
    0.71
     Surviv
    0.70
     quét
    0.69
     xvii
    0.68
     Env
    0.68
     Pancakes
    0.68
    Act Density 0.008%

    No Known Activations