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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     balance
    -1.81
     Balance
    -1.66
     BALANCE
    -1.48
    Balance
    -1.40
    balance
    -1.37
     balans
    -1.25
    BALANCE
    -1.22
     balanced
    -1.13
     balances
    -1.12
     équilibre
    -1.09
    POSITIVE LOGITS
     the
    0.66
     problems
    0.56
     that
    0.55
     Meksiku
    0.55
    migrationBuilder
    0.54
     implications
    0.53
    UrlResolution
    0.53
     concerns
    0.52
     than
    0.52
    NameInMap
    0.52
    Act Density 0.043%

    No Known Activations