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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     captivity
    -0.07
    ุทธ
    -0.07
    inka
    -0.07
     проект
    -0.06
     protocols
    -0.06
    _receive
    -0.06
    _outer
    -0.06
    .RemoveEmptyEntries
    -0.06
    servername
    -0.06
     duplicates
    -0.06
    POSITIVE LOGITS
    Posted
    0.07
    _DE
    0.06
    0.06
     rib
    0.06
    症
    0.06
     fres
    0.06
     vừa
    0.06
     Fransız
    0.06
    /st
    0.06
    #region
    0.06
    Act Density 0.001%

    No Known Activations