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

    Neuronpedia

    INDEX
    Explanations

    opinions and analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worried
    -0.07
     Deprecated
    -0.06
    ]];
    -0.06
     Henry
    -0.06
    Public
    -0.06
    وند
    -0.06
    ék
    -0.06
     states
    -0.06
     Critics
    -0.06
    ra
    -0.06
    POSITIVE LOGITS
    šil
    0.08
    часно
    0.07
    ислов
    0.07
     RESET
    0.06
    ildenafil
    0.06
     싱글
    0.06
    .Reporting
    0.06
    ublished
    0.06
     Mixing
    0.06
    /application
    0.06
    Act Density 0.109%

    No Known Activations