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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron detects numeric version strings and version constraints (e.g. “4.0.0”, “>=4.0.0”, “1.2.3”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ImGui
    -0.07
     X
    -0.07
    aign
    -0.07
     splits
    -0.06
    ุ่
    -0.06
    _spawn
    -0.06
     TextInputType
    -0.06
    _tuples
    -0.06
     optics
    -0.06
    million
    -0.06
    POSITIVE LOGITS
     btn
    0.07
    aho
    0.06
     히
    0.06
    Quick
    0.06
    /operator
    0.06
     EXCEPTION
    0.06
    ========
    0.06
     guides
    0.06
    -profit
    0.06
    hoe
    0.06
    Act Density 0.010%

    No Known Activations