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

    Neuronpedia

    INDEX
    Explanations

    .o

    np_max-act · gemini-2.0-flash

    The neuron fires on references to object‐file targets (the “.o” filenames and related “objs” tokens) in build/Makefile text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    reten
    -0.08
    "For
    -0.07
    (ver
    -0.07
    THOOK
    -0.07
     rendre
    -0.06
    .WriteByte
    -0.06
    ienia
    -0.06
     itemBuilder
    -0.06
    觉得
    -0.06
    iß
    -0.06
    POSITIVE LOGITS
     engines
    0.08
     HttpHeaders
    0.07
    υκ
    0.07
     telecom
    0.07
     ^↵
    0.06
     nine
    0.06
     Breast
    0.06
    741
    0.06
     ра
    0.06
     Mandela
    0.06
    Act Density 0.002%

    No Known Activations