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

    Neuronpedia

    INDEX
    Explanations

    wrapper

    np_max-act · gemini-2.0-flash

    This neuron detects CSS class selectors (identifiers beginning with a dot) in style or template code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    BeginInit
    -0.07
     artillery
    -0.07
    _rooms
    -0.06
    .AdapterView
    -0.06
    Serv
    -0.06
    /product
    -0.06
    Ger
    -0.06
    _TOUCH
    -0.06
    Analy
    -0.06
    =";↵
    -0.06
    POSITIVE LOGITS
    forma
    0.07
     kro
    0.07
    副
    0.07
    _container
    0.06
    warehouse
    0.06
     kims
    0.06
    0.06
     Container
    0.06
     vero
    0.06
    cj
    0.06
    Act Density 0.011%

    No Known Activations