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

    Neuronpedia

    INDEX
    Explanations

    Negative tone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tariff
    -0.07
    анной
    -0.07
    [Y
    -0.06
     stake
    -0.06
    DataBase
    -0.06
    dh
    -0.06
     آرام
    -0.06
    (name
    -0.06
    �
    -0.06
    beer
    -0.06
    POSITIVE LOGITS
     sitting
    0.06
     Cham
    0.06
     vect
    0.06
     World
    0.06
     фунда
    0.06
     Tic
    0.06
     newSize
    0.06
     Cos
    0.06
     Liv
    0.06
    /background
    0.06
    Act Density 0.139%

    No Known Activations