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

    Neuronpedia

    INDEX
    Explanations

    cut

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.78
     nahilalakip
    -0.75
    Portale
    -0.72
     CreateTagHelper
    -0.63
     Waray
    -0.59
     autorytatywna
    -0.59
     дописавши
    -0.58
    titleMargin
    -0.57
    MessageTagHelper
    -0.57
     &___
    -0.57
    POSITIVE LOGITS
     the
    0.48
     Pièces
    0.44
     onBackPressed
    0.44
     Speck
    0.44
     FID
    0.43
     Policing
    0.43
    قديم
    0.43
    Salta
    0.42
     mustard
    0.42
     Cracking
    0.41
    Act Density 0.002%

    No Known Activations