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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quite
    -0.81
    ous
    -0.76
    quite
    -0.72
    Quite
    -0.64
     Quite
    -0.64
     oreilles
    -0.59
     judiciales
    -0.58
     siguran
    -0.58
     plain
    -0.57
     fédé
    -0.56
    POSITIVE LOGITS
    DockStyle
    0.69
     kaarangay
    0.66
     nahilalakip
    0.65
    GIVEREF
    0.61
    NUMX
    0.58
    ivy
    0.56
    ContentLoaded
    0.55
     acquis
    0.54
     species
    0.51
    InputTagHelper
    0.51
    Act Density 0.096%

    No Known Activations