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
     Arbeit
    -0.08
    etus
    -0.07
     Laud
    -0.07
     результ
    -0.06
     spanking
    -0.06
     regul
    -0.06
     Fletcher
    -0.06
    !!)↵
    -0.06
     Aydın
    -0.06
    .Roll
    -0.06
    POSITIVE LOGITS
     [{↵
    0.07
     бли
    0.06
    sequelize
    0.06
    Dummy
    0.06
     зап
    0.06
     ще
    0.05
    igits
    0.05
    LEN
    0.05
    uide
    0.05
    tahun
    0.05
    Act Density 0.005%

    No Known Activations