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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash

    This neuron fires on HTML attribute–value tokens, specifically fragments of CSS class and id names (e.g. “mem,” “esc,” “MSearch,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    OV
    -0.07
     Tyson
    -0.07
     lateinit
    -0.07
     Todd
    -0.07
    RU
    -0.06
    IZER
    -0.06
    ढ
    -0.06
     Cait
    -0.06
    Personal
    -0.06
    SSF
    -0.06
    POSITIVE LOGITS
     boto
    0.07
    repositories
    0.07
    /cl
    0.06
    Logged
    0.06
    	rv
    0.06
     programmer
    0.06
    details
    0.06
     francouz
    0.06
    assword
    0.06
    .Contact
    0.06
    Act Density 0.002%

    No Known Activations