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

    Neuronpedia

    INDEX
    Explanations

    three

    np_max-act · gemini-2.0-flash

    The neuron activates on Three.js–specific class and method names (e.g. “THREE.Scene,” “WebGLRenderer,” “OrbitControls,” etc.), i.e. it’s detecting Three.js code constructs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _mA
    -0.07
    년도
    -0.06
    .Actor
    -0.06
     Blades
    -0.06
    _ORIENTATION
    -0.06
    PP
    -0.06
     пода
    -0.06
    imulation
    -0.06
     GPL
    -0.06
    _INTERVAL
    -0.06
    POSITIVE LOGITS
     enhancement
    0.07
     Implicit
    0.07
    getLast
    0.07
     midst
    0.07
    ellery
    0.07
     Chinese
    0.07
     Blur
    0.06
     chinese
    0.06
    
    0.06
    listing
    0.06
    Act Density 0.007%

    No Known Activations