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

    Neuronpedia

    INDEX
    Explanations

    envelope

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.02
     Anſ
    -0.99
     Monfieur
    -0.98
    ſelf
    -0.98
     Theſe
    -0.96
     Efq
    -0.93
     faſt
    -0.91
     pandemic
    -0.90
     iſt
    -0.90
     itſelf
    -0.90
    POSITIVE LOGITS
    e
    0.50
     of
    0.48
     d
    0.46
    ----------------
    0.43
    '
    0.42
     "
    0.42
    лька
    0.41
    "
    0.40
    V
    0.40
     '
    0.40
    Act Density 0.038%

    No Known Activations