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

    Neuronpedia

    INDEX
    Explanations

    words related to providing or getting help with assignments, especially engineering assignments

    oai_token-act-pair · gemini-2.0-flash

    tech related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.94
     فريبيس
    -0.93
    parsedMessage
    -0.87
    aarrggbb
    -0.85
    +#+#
    -0.84
     autorytatywna
    -0.82
     mergeFrom
    -0.81
     <>",
    -0.79
    клопе
    -0.77
    ſelves
    -0.77
    POSITIVE LOGITS
     d
    0.45
     where
    0.45
     ※
    0.44
     g
    0.43
     r
    0.43
     Little
    0.41
     k
    0.41
    ός
    0.40
     waar
    0.40
    al
    0.39
    Act Density 1.027%

    No Known Activations