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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    California
    -0.07
    oted
    -0.07
    -type
    -0.07
    PIP
    -0.07
    ots
    -0.07
     BP
    -0.07
     OD
    -0.06
     fourth
    -0.06
     hoặc
    -0.06
     fungus
    -0.06
    POSITIVE LOGITS
     unitOfWork
    0.06
     Casa
    0.06
     человек
    0.06
     kaum
    0.06
    .TextAlign
    0.06
    de
    0.06
    \Services
    0.06
    .LogWarning
    0.06
     Trucks
    0.06
    #endregion
    0.06
    Act Density 0.058%

    No Known Activations