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

    Neuronpedia

    INDEX
    Explanations

    leader

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.04
     وتسجيلات
    -0.76
     Roskov
    -0.72
    ReusableCell
    -0.67
     lenker
    -0.64
    astéro
    -0.63
    Mothers
    -0.61
    wpi
    -0.59
    曖昧さ回避
    -0.58
     TeV
    -0.57
    POSITIVE LOGITS
     leader
    0.75
     head
    0.75
     Head
    0.71
     des
    0.66
    Head
    0.64
    CodedInputStream
    0.62
     man
    0.60
    head
    0.59
     ruler
    0.54
     sitting
    0.52
    Act Density 0.001%

    No Known Activations