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

    Neuronpedia

    INDEX
    Explanations

    harmonics

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of spherical harmonics (or spherical‐harmonic transforms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lan
    -0.07
    amazon
    -0.07
     Dom
    -0.07
    reviews
    -0.07
     medical
    -0.06
     workflows
    -0.06
     bible
    -0.06
     kont
    -0.06
     Z
    -0.06
     Cole
    -0.06
    POSITIVE LOGITS
     mismatch
    0.07
    (stypy
    0.06
    込
    0.06
     =~
    0.06
    structors
    0.06
    ‫
    0.06
    (adapter
    0.06
    "=>"
    0.06
    �
    0.06
    余
    0.06
    Act Density 0.007%

    No Known Activations