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

    Neuronpedia

    INDEX
    Explanations

    stay

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     téléchargez
    -0.64
    UpInside
    -0.60
     Krone
    -0.60
     disambiguazione
    -0.58
    KommentareTeilen
    -0.55
    Carriera
    -0.53
    ContentAsync
    -0.53
    MessageOf
    -0.50
    verifyException
    -0.50
     وتسجيلات
    -0.50
    POSITIVE LOGITS
     gold
    0.61
     golden
    0.59
    UnsafeEnabled
    0.56
     weird
    0.55
    componentWill
    0.52
     Gold
    0.51
     GOLD
    0.50
     متحده
    0.50
     gouden
    0.49
    stagland
    0.49
    Act Density 0.001%

    No Known Activations