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

    Neuronpedia

    INDEX
    Explanations

    keywords related to modules, error messages, and database interactions

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

    Code snippets; file paths

    np_acts-logits-general · gemini-2.0-flash

    closing code string delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),”
    -0.88
    ).”
    -0.84
    )”
    -0.76
    ?”
    -0.72
    ],"
    -0.70
    ]."
    -0.68
    )."
    -0.68
    ),"
    -0.67
    ;">
    -0.67
    ]",
    -0.66
    POSITIVE LOGITS
     lenker
    1.14
     незавершена
    1.11
    ыгана
    0.90
    uxxxx
    0.88
    GraphicsUnit
    0.86
    COUVER
    0.82
     ProtoMessage
    0.82
    ніципалі
    0.82
     kasarigan
    0.81
    tvguidetime
    0.81
    Act Density 0.480%

    No Known Activations