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

    Neuronpedia

    INDEX
    Explanations

    relationship

    np_max-act · gemini-2.0-flash

    The neuron detects terms that introduce or describe relationships or associations between variables (e.g. “relationship,” “between,” “among”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cookbook
    -0.06
     обра
    -0.06
     dày
    -0.06
    _bundle
    -0.06
    Mixin
    -0.06
     ос
    -0.06
    cco
    -0.06
     modificar
    -0.06
    ]+)/
    -0.06
    .Total
    -0.06
    POSITIVE LOGITS
     زمینه
    0.08
     illeg
    0.07
    ogr
    0.07
    YN
    0.07
     meaningless
    0.07
    .Concat
    0.07
    .lang
    0.07
     ني
    0.07
    ische
    0.07
    ん
    0.07
    Act Density 0.013%

    No Known Activations