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

    Neuronpedia

    INDEX
    Explanations

    multiple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bucket
    -0.07
     Engagement
    -0.07
     felt
    -0.06
     Riv
    -0.06
     fuel
    -0.06
     lept
    -0.06
     boom
    -0.06
     agencies
    -0.06
     overrun
    -0.06
     buckets
    -0.06
    POSITIVE LOGITS
     Associates
    0.08
    ège
    0.07
    Downloads
    0.07
    pectives
    0.06
    -Л
    0.06
     titul
    0.06
    UNG
    0.06
    ประโยชน
    0.06
    мента
    0.06
    模式
    0.06
    Act Density 0.002%

    No Known Activations