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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric CSS values (e.g. “100%”, “50px”) in style declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Date
    -0.06
     célib
    -0.06
    tm
    -0.06
    _d
    -0.06
     Colonial
    -0.06
     đào
    -0.06
    }><
    -0.06
    #a
    -0.06
     eski
    -0.06
     moder
    -0.06
    POSITIVE LOGITS
    \Repositories
    0.07
     oblast
    0.06
     لو
    0.06
     Krishna
    0.06
    Д
    0.06
     Nguyen
    0.06
    레
    0.06
    фіка
    0.06
     гра
    0.06
     округ
    0.05
    Act Density 0.003%

    No Known Activations