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

    Neuronpedia

    INDEX
    Explanations

    Mathematical normal derivatives

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the Greek letter “nu,” especially in boundary‐normal derivative notation (∂_ν) and related boundary terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    moved
    -0.07
    .Manifest
    -0.06
    Plane
    -0.06
     content
    -0.06
     Naples
    -0.06
     IntelliJ
    -0.06
    -trained
    -0.06
     plains
    -0.06
    _marker
    -0.06
    .mk
    -0.06
    POSITIVE LOGITS
     sexually
    0.08
    発売
    0.07
    egt
    0.06
    режд
    0.06
    \"",
    0.06
     Τζ
    0.06
     vulner
    0.06
     controle
    0.06
     сайті
    0.06
     受
    0.06
    Act Density 0.004%

    No Known Activations