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

    Neuronpedia

    INDEX
    Explanations

    ==

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Sc
    -0.07
     Devon
    -0.07
    住宅
    -0.07
    Deserialize
    -0.07
     devoted
    -0.07
    再也没有
    -0.07
    还原
    -0.07
     detained
    -0.07
    .AspNetCore
    -0.07
    .download
    -0.06
    POSITIVE LOGITS
    oras
    0.08
    Ⱑ
    0.07
    agnar
    0.07
    יצו
    0.07
     Willie
    0.07
    ancellationToken
    0.07
     ")"↵
    0.06
     Horm
    0.06
     fighters
    0.06
     fiance
    0.06
    Act Density 0.002%

    No Known Activations