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

    Neuronpedia

    INDEX
    Explanations

    are/were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sid
    -0.07
    ()});↵
    -0.07
    、彼
    -0.06
     suo
    -0.06
    اها
    -0.06
    CFG
    -0.06
    inu
    -0.06
     onlar
    -0.06
     너
    -0.06
     hamburger
    -0.06
    POSITIVE LOGITS
    ský
    0.07
     зас
    0.06
     BİR
    0.06
    .consume
    0.06
    IT
    0.06
     lear
    0.06
    .music
    0.06
    accuracy
    0.06
    imp
    0.06
    ultur
    0.06
    Act Density 0.143%

    No Known Activations