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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron activates on contrastive discourse markers—especially the adversative connector “however.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    цо
    -0.07
    的心
    -0.06
    .Post
    -0.06
    Meet
    -0.06
    Density
    -0.06
    ih
    -0.06
    _VARIABLE
    -0.06
     Ged
    -0.06
    cai
    -0.06
     Bethesda
    -0.06
    POSITIVE LOGITS
     však
    0.07
    _unix
    0.06
    lius
    0.06
    λικ
    0.06
     zelf
    0.06
    .navCtrl
    0.06
     Alic
    0.06
    ysql
    0.06
     usted
    0.06
    udden
    0.06
    Act Density 0.025%

    No Known Activations