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

    Neuronpedia

    INDEX
    Explanations

    code and nodes

    np_max-act · gemini-2.0-flash

    The neuron detects method or function names invoked on objects in code, i.e. tokens appearing after a dot that represent API calls or chained methods.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ellas
    -0.07
    альний
    -0.07
     Thumbnail
    -0.07
     треба
    -0.07
     němu
    -0.07
    골
    -0.07
    UND
    -0.07
     lens
    -0.06
     ngại
    -0.06
    	dist
    -0.06
    POSITIVE LOGITS
     Wal
    0.06
     nearing
    0.06
     MH
    0.06
     Nev
    0.06
     pada
    0.06
     Comic
    0.06
    ерп
    0.06
     इन
    0.06
    ὶ
    0.06
    sun
    0.06
    Act Density 0.060%

    No Known Activations