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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash

    This neuron detects transitional discourse markers, especially the phrase “At this point.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	JPanel
    -0.06
    Bin
    -0.06
     reasoning
    -0.06
     служ
    -0.06
    Ohio
    -0.06
    ilim
    -0.06
     دلیل
    -0.06
     painter
    -0.05
     genel
    -0.05
     será
    -0.05
    POSITIVE LOGITS
    �
    0.09
    خصص
    0.07
    Accordion
    0.07
    сько
    0.07
    .Time
    0.07
    ipi
    0.07
     مقد
    0.07
    _imm
    0.07
    district
    0.06
    dark
    0.06
    Act Density 0.011%

    No Known Activations