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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron fires on markup tag syntax, i.e. the angle-bracketed HTML/XML tags themselves.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _MIDDLE
    -0.07
     behave
    -0.07
     exported
    -0.06
     makeshift
    -0.06
     consecutive
    -0.06
     cached
    -0.06
    toBeDefined
    -0.06
     Helen
    -0.06
    有些
    -0.06
     getAll
    -0.06
    POSITIVE LOGITS
     spiral
    0.07
    InView
    0.07
     Relief
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    sounds
    0.06
     massages
    0.06
    تس
    0.06
    NV
    0.06
     
↵ 
↵
    0.06
     Chapel
    0.06
    Act Density 0.028%

    No Known Activations