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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InSection
    -0.61
     فريبيس
    -0.60
     boî
    -0.60
    enterOuterAlt
    -0.58
     phénomènes
    -0.58
     dieux
    -0.58
     lumières
    -0.58
     vérit
    -0.57
     télécharge
    -0.55
     tamaños
    -0.55
    POSITIVE LOGITS
     balls
    0.67
     bricks
    0.65
    <bos>
    0.65
     pencils
    0.61
     slabs
    0.60
     lumps
    0.59
     cakes
    0.59
     crayons
    0.58
     contextLoads
    0.57
     cake
    0.56
    Act Density 0.020%

    No Known Activations