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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eachtet
    -0.48
    ectady
    -0.47
     amely
    -0.47
     defaultstate
    -0.46
     dasar
    -0.45
    žek
    -0.44
     ingår
    -0.43
     usarlo
    -0.43
    рги
    -0.43
     devons
    -0.43
    POSITIVE LOGITS
     initComponents
    0.69
    DockStyle
    0.65
    AccessorTable
    0.61
     a
    0.58
    TagHelper
    0.57
     brief
    0.55
     billboards
    0.55
     piped
    0.54
     puffs
    0.54
     BRIEF
    0.54
    Act Density 0.003%

    No Known Activations