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

    Neuronpedia

    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Du
    -0.06
    actus
    -0.06
     усіх
    -0.06
    ัพ
    -0.06
    coon
    -0.06
    sterdam
    -0.06
     никто
    -0.06
    -acre
    -0.06
    ردد
    -0.06
    .Context
    -0.06
    POSITIVE LOGITS
     Trinidad
    0.07
    贝
    0.07
     meas
    0.06
    ding
    0.06
    ΑΛ
    0.06
    ARATION
    0.06
     dealership
    0.06
     subsidiary
    0.06
    253
    0.06
    firm
    0.06
    Act Density 0.001%

    No Known Activations