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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash

    This neuron fires on raw HTML tag tokens (e.g. the tag names like “B”, “A”, “FONT” inside angle brackets).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Thanks
    -0.06
    -aff
    -0.06
    705
    -0.06
    Groups
    -0.06
    iment
    -0.06
    uniform
    -0.06
    unately
    -0.06
    statement
    -0.06
    ็ม
    -0.06
    ใหม
    -0.06
    POSITIVE LOGITS
     kuru
    0.07
     CGPoint
    0.06
     linspace
    0.06
     publik
    0.06
    ;amp
    0.06
     관리자
    0.06
    .Forms
    0.06
    iselect
    0.06
     của
    0.06
    스의
    0.06
    Act Density 0.002%

    No Known Activations