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

    Neuronpedia

    INDEX
    Explanations

    detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    增加
    -0.07
     cầu
    -0.07
     đạt
    -0.07
    ):(
    -0.07
     tvoř
    -0.07
    lardır
    -0.07
    倍
    -0.07
    ทาน
    -0.07
    しか
    -0.07
    受
    -0.07
    POSITIVE LOGITS
     camer
    0.06
    ávající
    0.06
    _resp
    0.06
     inhabit
    0.06
    جه
    0.06
     Cowboy
    0.06
     Choosing
    0.06
    ueue
    0.06
     Helps
    0.06
     format
    0.06
    Act Density 0.027%

    No Known Activations