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

    Neuronpedia

    INDEX
    Explanations

    International relations and organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.07
     betweenstory
    -1.02
    ſelf
    -0.98
     purpoſe
    -0.97
     itſelf
    -0.96
     myſelf
    -0.96
     ainfi
    -0.94
    <bos>
    -0.93
     pleaſure
    -0.93
     Monfieur
    -0.93
    POSITIVE LOGITS
     
    0.65
     (
    0.53
     .
    0.53
     West
    0.53
     The
    0.53
     Human
    0.53
     National
    0.52
     Fore
    0.51
     UN
    0.50
    ↵↵
    0.49
    Act Density 0.050%

    No Known Activations