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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron responds to tokens that look like multiword, mixed‐case identifiers or titles (e.g. CamelCase/PascalCase names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     legends
    -0.06
    nds
    -0.06
    .API
    -0.06
    ossed
    -0.06
    enden
    -0.06
     edged
    -0.06
     colors
    -0.06
    Individual
    -0.06
    PLIED
    -0.06
     DAY
    -0.06
    POSITIVE LOGITS
    یش
    0.07
     річ
    0.07
    Texture
    0.06
    (Graphics
    0.06
     yatırım
    0.06
    (HaveOccurred
    0.06
     invoice
    0.06
    (eval
    0.06
    шов
    0.06
     ارزی
    0.06
    Act Density 0.066%

    No Known Activations