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

    Neuronpedia

    INDEX
    Explanations

    lost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stool
    -0.08
    ｔ
    -0.07
     months
    -0.07
     לג
    -0.07
    מא
    -0.07
    (Key
    -0.06
     detention
    -0.06
     Lt
    -0.06
    .Pos
    -0.06
     <+
    -0.06
    POSITIVE LOGITS
    씻
    0.07
     Backpack
    0.07
    ibbon
    0.07
    쏴
    0.06
     Commod
    0.06
    会产生
    0.06
    셒
    0.06
     gravy
    0.06
     pharmacist
    0.06
     useCallback
    0.06
    Act Density 0.032%

    No Known Activations