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

    Neuronpedia

    INDEX
    Explanations

    mailing label account information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .FLAG
    -0.07
    .gamma
    -0.07
     하고
    -0.07
    (confirm
    -0.06
    /Admin
    -0.06
    見え
    -0.06
     finance
    -0.06
    (nt
    -0.06
    	points
    -0.06
    ວ
    -0.06
    POSITIVE LOGITS
    凘
    0.07
    プラン
    0.07
    喈
    0.07
     miracles
    0.07
    轻松
    0.06
    leş
    0.06
    -about
    0.06
     massac
    0.06
    趄
    0.06
    把持
    0.06
    Act Density 0.048%

    No Known Activations