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

    Neuronpedia

    INDEX
    Explanations

    Pie

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “Pie Chart,” i.e. references to pie-chart plotting.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     walk
    -0.07
     drop
    -0.07
    .hw
    -0.06
    	b
    -0.06
     ",↵
    -0.06
     lowering
    -0.06
     hứ
    -0.06
    _step
    -0.06
    anst
    -0.06
    Give
    -0.06
    POSITIVE LOGITS
     مواط
    0.07
    =settings
    0.06
     JPEG
    0.06
     criar
    0.06
     PLC
    0.06
     関連
    0.06
     Adrian
    0.06
     أق
    0.06
     funded
    0.06
    ."""↵
    0.06
    Act Density 0.007%

    No Known Activations