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

    Neuronpedia

    INDEX
    Explanations

    faculty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apps
    -0.07
     mining
    -0.07
     Snapchat
    -0.07
     deport
    -0.07
    роф
    -0.07
     gc
    -0.06
    =event
    -0.06
    地球
    -0.06
     |\
    -0.06
    etim
    -0.06
    POSITIVE LOGITS
    ibilities
    0.06
     Gly
    0.06
    щается
    0.06
    vented
    0.06
    faculty
    0.06
    lations
    0.06
    favorite
    0.05
    .global
    0.05
     пода
    0.05
    .Child
    0.05
    Act Density 0.002%

    No Known Activations