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

    Neuronpedia

    INDEX
    Explanations

    Journal of Applied Physics

    np_max-act · gemini-2.0-flash

    This neuron activates on journal citation tokens (e.g., “Appl” and “Phys”) indicating references to scientific publications.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    como
    -0.07
    MATRIX
    -0.07
    rio
    -0.07
    _closure
    -0.07
     evrop
    -0.06
     typings
    -0.06
     Epic
    -0.06
    /memory
    -0.06
     alunos
    -0.06
    frames
    -0.06
    POSITIVE LOGITS
    願い
    0.07
    嘴
    0.07
     зак
    0.07
    ?):
    0.06
    _idle
    0.06
    	opts
    0.06
     groupId
    0.06
     need
    0.06
    弄
    0.06
    _seg
    0.06
    Act Density 0.005%

    No Known Activations