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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron activates on inline reference/citation and section-label markers (e.g. bracketed citation keys, numbered section tags, and related formatting tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    \Services
    -0.06
    =g
    -0.06
     جنوب
    -0.06
     Odd
    -0.06
    čel
    -0.06
     лич
    -0.06
     icy
    -0.05
     üzerinde
    -0.05
     heightFor
    -0.05
     chica
    -0.05
    POSITIVE LOGITS
    ₂
    0.08
     거
    0.07
    laması
    0.07
    "</
    0.07
    �
    0.06
     Chính
    0.06
    asm
    0.06
     **/↵↵
    0.06
     technicians
    0.06
    วง
    0.06
    Act Density 0.000%

    No Known Activations