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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    理念
    -0.08
    ington
    -0.08
    ూ�
    -0.08
    iode
    -0.08
    ']?>"
    -0.08
     dedication
    -0.08
    smanship
    -0.08
     qualités
    -0.08
    的重要
    -0.08
    ///<
    -0.08
    POSITIVE LOGITS
     blurry
    0.09
     Schwierigkeiten
    0.08
     manque
    0.08
     clogged
    0.08
     bị
    0.08
     insufficient
    0.08
    乱码
    0.08
     troubleshoot
    0.08
     incompat
    0.08
     аллерг
    0.08
    Act Density 0.005%

    No Known Activations