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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    The neuron is especially sensitive to numeric literals (especially floating-point numbers) embedded in HTML/XML boilerplate.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     HV
    -0.06
    存
    -0.06
    _UL
    -0.06
     emulation
    -0.06
    随
    -0.06
     settling
    -0.06
     kullanıcı
    -0.06
    .requireNonNull
    -0.06
    ่ต
    -0.06
    fan
    -0.06
    POSITIVE LOGITS
    .GetKeyDown
    0.06
    ooter
    0.06
    struments
    0.06
    _vertices
    0.06
    KeyId
    0.06
    .ipv
    0.06
    nvarchar
    0.06
    (right
    0.06
    /styles
    0.06
     تغ
    0.06
    Act Density 0.007%

    No Known Activations