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

    Neuronpedia

    INDEX
    Explanations

    net

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =tmp
    -0.07
    ียว
    -0.07
     Danish
    -0.07
     toddlers
    -0.07
    庆
    -0.07
    ΙΣ
    -0.06
     giản
    -0.06
     Chu
    -0.06
    ався
    -0.06
     Brexit
    -0.06
    POSITIVE LOGITS
    peaker
    0.06
    appropri
    0.06
    iễn
    0.06
     UnityEngine
    0.06
     swath
    0.06
    セット
    0.06
    pers
    0.06
    оти
    0.06
    .dict
    0.06
    Operations
    0.06
    Act Density 0.004%

    No Known Activations