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

    Neuronpedia

    INDEX
    Explanations

    added

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     washing
    -0.07
    monkey
    -0.07
    eree
    -0.06
     Joyce
    -0.06
     cumulative
    -0.06
    Haunted
    -0.06
     contraseña
    -0.06
    .now
    -0.06
    .cos
    -0.06
     kter
    -0.06
    POSITIVE LOGITS
     Απο
    0.07
     �
    0.07
    BundleOrNil
    0.07
    .Exec
    0.07
    游戏
    0.06
     Appalachian
    0.06
    到底
    0.06
     فار
    0.06
     кін
    0.06
     wildfire
    0.06
    Act Density 0.001%

    No Known Activations