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

    Neuronpedia

    INDEX
    Explanations

    Numbered lists

    np_max-act · gemini-2.0-flash

    The neuron activates on HTML/XML-like markup tokens (e.g. “<ol start=…>” tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     розвит
    -0.07
    akens
    -0.07
    FX
    -0.07
    生
    -0.07
     gfx
    -0.06
    Derived
    -0.06
    	animation
    -0.06
    .exc
    -0.06
     RUNNING
    -0.06
     방문
    -0.06
    POSITIVE LOGITS
    ubo
    0.06
    -ne
    0.06
    گار
    0.06
    0.06
     WAS
    0.06
     mujer
    0.06
     кас
    0.06
    UnitOfWork
    0.06
     nuestros
    0.06
     Mothers
    0.06
    Act Density 0.004%

    No Known Activations