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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zostać
    -0.08
    andid
    -0.07
    ân
    -0.07
     causa
    -0.07
     essen
    -0.07
    概
    -0.07
    Sand
    -0.07
    <Text
    -0.07
    SUCCESS
    -0.06
    历程
    -0.06
    POSITIVE LOGITS
    ,arg
    0.07
    不屑
    0.07
    Protection
    0.07
     tits
    0.07
    .report
    0.07
    .Restr
    0.07
    合约
    0.07
     Permissions
    0.07
    printStats
    0.07
     yönetim
    0.07
    Act Density 0.000%

    No Known Activations