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

    Neuronpedia

    INDEX
    Explanations

    filenames

    np_max-act · gemini-2.0-flash

    numbers, especially numeric literals (including floating-point values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ResponseType
    -0.07
    .Flag
    -0.06
    -Length
    -0.06
     cig
    -0.06
    へ
    -0.06
     feat
    -0.06
    TIMER
    -0.06
    せ
    -0.06
    _skin
    -0.06
     diabetic
    -0.06
    POSITIVE LOGITS
    -roll
    0.06
    ัวร
    0.06
     اختیار
    0.06
    atural
    0.06
    brook
    0.06
     Threshold
    0.06
    (""
    0.06
    $conn
    0.06
     Former
    0.06
    notin
    0.06
    Act Density 0.035%

    No Known Activations