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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fx
    -0.08
    Elements
    -0.07
     MMI
    -0.07
    保卫
    -0.07
    Encode
    -0.07
    .Files
    -0.07
    ǣ
    -0.07
    OE
    -0.07
    .Stat
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    uable
    0.07
    涵盖
    0.06
    ////////////////////////////////
    0.06
    unknown
    0.06
     чуть
    0.06
    aways
    0.06
    wer
    0.06
    Recursive
    0.06
    .mon
    0.06
    镢
    0.06
    Act Density 0.062%

    No Known Activations