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

    Neuronpedia

    INDEX
    Explanations

    raw

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens belonging to code excerpts—especially Python identifiers and function‐call names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     र
    -0.06
     Für
    -0.06
    ISON
    -0.06
     DMA
    -0.06
    294
    -0.06
    )-
    -0.06
    allocator
    -0.06
     jejichž
    -0.06
    상의
    -0.06
    สง
    -0.06
    POSITIVE LOGITS
     }↵↵↵↵↵↵
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵
    0.06
    .Nome
    0.06
    очный
    0.06
    candidates
    0.06
    Profiler
    0.06
    itate
    0.06
     mech
    0.06
    -relative
    0.06
     غير
    0.06
    Act Density 0.328%

    No Known Activations