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

    Neuronpedia

    INDEX
    Explanations

    header files

    np_max-act · gemini-2.0-flash

    The neuron fires on header‐file tokens—i.e. parts of include paths ending in “.h.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    so
    -0.07
     voices
    -0.06
    .AddComponent
    -0.06
     middleware
    -0.06
    sembled
    -0.06
     surely
    -0.06
     relaxing
    -0.06
    배
    -0.06
     انج
    -0.06
     Sgt
    -0.06
    POSITIVE LOGITS
    .hasNext
    0.07
    яж
    0.07
    Ticket
    0.06
     totals
    0.06
    ]↵↵
    0.06
     Acad
    0.06
    εις
    0.06
     відмов
    0.06
    values
    0.06
     scratching
    0.06
    Act Density 0.026%

    No Known Activations