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

    Neuronpedia

    INDEX
    Explanations

    requests for information or explanations

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

    reporting information or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.50
    PageRoute
    -0.49
    wapV
    -0.48
    RegressionTest
    -0.44
    PyExc
    -0.42
     للاسماء
    -0.42
     Bluestacks
    -0.41
     HttpNotFound
    -0.41
     refining
    -0.41
    CppMethod
    -0.40
    POSITIVE LOGITS
     tells
    1.13
     told
    1.12
     tell
    1.09
    Told
    1.04
     telling
    1.01
     Told
    1.01
     Tells
    0.99
     TELL
    0.94
     Telling
    0.92
    told
    0.91
    Act Density 0.090%

    No Known Activations