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

    Neuronpedia

    INDEX
    Explanations

    Wordpress code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    教え
    -0.07
    ثقافة
    -0.07
    heat
    -0.07
     spar
    -0.07
     suitcase
    -0.07
     naz
    -0.07
    훗
    -0.07
    自救
    -0.07
     typeId
    -0.07
     기타
    -0.07
    POSITIVE LOGITS
    contra
    0.07
    𬣳
    0.07
    ligne
    0.07
    магазин
    0.07
    #![
    0.07
    必将
    0.07
     continuation
    0.06
     rall
    0.06
    县级
    0.06
    俅
    0.06
    Act Density 0.002%

    No Known Activations