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

    Neuronpedia

    INDEX
    Explanations

    -label

    np_max-act · gemini-2.0-flash

    This neuron detects Bootstrap form labels marked with the “control‐label” class.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     protocols
    -0.07
    pthread
    -0.07
     timeval
    -0.06
     parad
    -0.06
    /pro
    -0.06
    .fetch
    -0.06
    Pending
    -0.06
    橋
    -0.06
    فته
    -0.06
    cluster
    -0.06
    POSITIVE LOGITS
    biology
    0.06
     Wikip
    0.06
     watching
    0.06
    少年
    0.06
     footnote
    0.06
     loud
    0.06
     scary
    0.06
    Liquid
    0.06
     investigate
    0.06
    ,"↵
    0.06
    Act Density 0.001%

    No Known Activations