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

    Neuronpedia

    INDEX
    Explanations

    the start and end of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or technical questions

    np_acts-logits-general · gemini-2.0-flash

    Q:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.99
     referenties
    -0.95
    DockStyle
    -0.90
    Rhestr
    -0.87
    GeneratedCode
    -0.84
    UnknownFields
    -0.81
    HomeAsUpEnabled
    -0.76
    DeleteBehavior
    -0.75
    Geplaatst
    -0.73
    ContentAlignment
    -0.73
    POSITIVE LOGITS
    »։
    0.53
     Sai
    0.47
    ')):
    0.45
    """.
    0.45
     lack
    0.44
    ']):
    0.44
    "]').
    0.44
    sproz
    0.44
    {%
    0.43
    ']").
    0.43
    Act Density 0.117%

    No Known Activations