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

    Neuronpedia

    INDEX
    Explanations

    Non-English and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     love
    -0.07
    φων
    -0.07
     Barker
    -0.07
    [u
    -0.07
     LOVE
    -0.07
     Climate
    -0.06
    Love
    -0.06
     Plex
    -0.06
    .AppendFormat
    -0.06
    urry
    -0.06
    POSITIVE LOGITS
    报告
    0.07
     βασ
    0.06
    .kwargs
    0.06
    限制
    0.06
     embarked
    0.06
    (remote
    0.06
     �
    0.06
     بررسی
    0.06
    .Tx
    0.06
     jsx
    0.06
    Act Density 0.009%

    No Known Activations