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

    Neuronpedia

    INDEX
    Explanations

    family members

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sville
    -0.07
    .getMethod
    -0.07
    .getFile
    -0.07
     swings
    -0.06
     purch
    -0.06
    previous
    -0.06
     toxin
    -0.06
    ınma
    -0.06
     adversity
    -0.06
     üzerindeki
    -0.06
    POSITIVE LOGITS
    _FEED
    0.06
    _DM
    0.06
    ihu
    0.06
     WWII
    0.06
     obsess
    0.06
     conn
    0.06
    :;↵
    0.06
    mom
    0.06
    STATE
    0.06
     DW
    0.06
    Act Density 0.051%

    No Known Activations