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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash

    This neuron detects HTML tag attribute assignments, i.e. attribute names followed by “=”.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Př
    -0.06
    WithName
    -0.06
     sober
    -0.06
     ucwords
    -0.06
     rizik
    -0.06
    ratio
    -0.06
    ribly
    -0.06
    adors
    -0.06
     پاورپوینت
    -0.06
    	editor
    -0.06
    POSITIVE LOGITS
    وسف
    0.08
     LW
    0.07
    SPORT
    0.06
     jurisdictions
    0.06
     KM
    0.06
     Jul
    0.06
     appName
    0.06
     Россия
    0.06
     druhý
    0.06
     Bình
    0.06
    Act Density 0.022%

    No Known Activations