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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive—it does not detect or respond to any tokens in these code examples.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ESS
    -0.07
     Whitney
    -0.07
     ediyorum
    -0.07
     HID
    -0.06
     ALWAYS
    -0.06
    spNet
    -0.06
     Dio
    -0.06
     foi
    -0.06
     nécessaire
    -0.06
    छ
    -0.06
    POSITIVE LOGITS
    \
    0.06
    (down
    0.06
     underestimated
    0.06
    Guid
    0.06
     exceptionally
    0.06
     revel
    0.06
     VALID
    0.06
     longest
    0.06
    لة
    0.06
     zahrani
    0.06
    Act Density 0.000%

    No Known Activations