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

    Neuronpedia

    INDEX
    Explanations

    tiers or levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DBC
    -0.08
     upper
    -0.07
     bedenken
    -0.07
     substitution
    -0.07
     directed
    -0.07
     precise
    -0.07
     gene
    -0.07
     gedaan
    -0.07
     word
    -0.07
     было
    -0.07
    POSITIVE LOGITS
    等级
    0.10
     tiers
    0.10
     tier
    0.10
    Tier
    0.09
     السنوات
    0.09
    tier
    0.09
     Tier
    0.09
    待遇
    0.08
     신규
    0.08
     erbjuder
    0.08
    Act Density 0.008%

    No Known Activations