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

    Neuronpedia

    INDEX
    Explanations

    tree

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of file‐system structure, activating on words like “directory” and “tree” in source comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (prog
    -0.07
    .grade
    -0.06
    atedRoute
    -0.06
    ації
    -0.06
    された
    -0.06
    pest
    -0.06
    pios
    -0.06
    _marker
    -0.06
    ellow
    -0.06
    аю
    -0.06
    POSITIVE LOGITS
     getChild
    0.07
     tener
    0.07
     biliyor
    0.06
    Solver
    0.06
    İR
    0.06
     NAV
    0.06
     Difference
    0.06
    mainwindow
    0.06
     owns
    0.06
     annihil
    0.06
    Act Density 0.001%

    No Known Activations