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

    Neuronpedia

    INDEX
    Explanations

    priv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hecy
    -0.07
     Zach
    -0.07
    ulant
    -0.07
    ічного
    -0.06
     Sug
    -0.06
     aer
    -0.06
    �
    -0.06
     tương
    -0.06
     Vak
    -0.06
    Insets
    -0.06
    POSITIVE LOGITS
    ήμερα
    0.07
    าว
    0.07
     maid
    0.07
     grip
    0.06
    ريقة
    0.06
     privately
    0.06
     Exiting
    0.06
    ppv
    0.06
    (bs
    0.06
    (hw
    0.06
    Act Density 0.003%

    No Known Activations