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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blanket
    -0.07
    hton
    -0.06
    Ret
    -0.06
    іли
    -0.06
     Guantanamo
    -0.06
     Cr
    -0.06
    enkins
    -0.06
     changer
    -0.06
     NC
    -0.06
    $L
    -0.06
    POSITIVE LOGITS
     rituals
    0.06
     حالت
    0.06
    .group
    0.06
    ROOM
    0.06
     nhạc
    0.06
    .Label
    0.06
    :start
    0.06
    Explore
    0.06
    |`↵
    0.06
     Putting
    0.06
    Act Density 0.000%

    No Known Activations