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

    Neuronpedia

    INDEX
    Explanations

    pack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    packs
    -0.82
    pack
    -0.81
    wiſe
    -0.75
     Monfieur
    -0.74
    ſelf
    -0.73
     Theſe
    -0.71
     onOptions
    -0.71
     Efq
    -0.68
     myſelf
    -0.66
     Majefty
    -0.65
    POSITIVE LOGITS
    umbledore
    0.58
    はじめに
    0.57
    numerusform
    0.55
     cherchés
    0.54
    OGND
    0.52
    ly
    0.48
    heroku
    0.46
     set
    0.46
    TagMode
    0.46
    jsdelivr
    0.45
    Act Density 1.526%

    No Known Activations