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

    Neuronpedia

    INDEX
    Explanations

    Kub

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diet
    -0.07
     komen
    -0.07
     picked
    -0.07
    People
    -0.06
     Thing
    -0.06
     genres
    -0.06
    Chinese
    -0.06
     companies
    -0.06
     dialogue
    -0.06
    ेल
    -0.06
    POSITIVE LOGITS
    .routing
    0.07
     줄
    0.06
     PartialView
    0.06
    AxisSize
    0.06
    achs
    0.06
    PIPE
    0.06
    ":[-
    0.06
     Connections
    0.06
     Barber
    0.06
    جو
    0.06
    Act Density 0.001%

    No Known Activations