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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and syntax

    oai_token-act-pair · gemini-2.0-flash

    File paths/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.56
     Мексичка
    -1.04
     Theſe
    -0.94
     pleaſure
    -0.92
     Савезне
    -0.88
     Efq
    -0.86
     itſelf
    -0.86
     myſelf
    -0.82
     fevere
    -0.78
     Majefty
    -0.78
    POSITIVE LOGITS
     []:
    0.65
     kasarigan
    0.59
     ...
    0.57
     ^=
    0.53
    celotti
    0.53
    meisterschaft
    0.51
     (“
    0.50
     #
    0.50
    ą
    0.50
    urlpatterns
    0.49
    Act Density 1.943%

    No Known Activations