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

    Neuronpedia

    INDEX
    Explanations

    examine/evaluate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    δ
    -0.08
     Quentin
    -0.07
    .addAction
    -0.07
    レン
    -0.07
    科协
    -0.07
     В
    -0.07
     troch
    -0.07
    --↵↵
    -0.07
    direction
    -0.07
    还想
    -0.07
    POSITIVE LOGITS
     서울
    0.07
     continually
    0.07
    JECT
    0.07
    milliseconds
    0.07
    uyo
    0.07
    แล
    0.07
    ########################################################################
    0.07
     kayıt
    0.06
    chrift
    0.06
     Yayın
    0.06
    Act Density 0.041%

    No Known Activations