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

    Neuronpedia

    INDEX
    Explanations

    Michael

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sex
    -0.06
     carved
    -0.06
     ува
    -0.06
     adversaries
    -0.06
    Budget
    -0.06
     Rit
    -0.06
     Carson
    -0.06
     ورد
    -0.06
    大家
    -0.06
     Exception
    -0.06
    POSITIVE LOGITS
    /of
    0.07
    nano
    0.07
    skému
    0.06
    .TEXTURE
    0.06
    rodní
    0.06
    скому
    0.06
     eder
    0.06
     hüc
    0.06
     Ρ
    0.06
     situations
    0.06
    Act Density 0.002%

    No Known Activations