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

    Neuronpedia

    INDEX
    Explanations

    New

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fos
    -0.07
    šlo
    -0.07
    cılar
    -0.06
    justice
    -0.06
     venture
    -0.06
     approaching
    -0.06
     füh
    -0.06
     await
    -0.06
     téléphone
    -0.06
     personnes
    -0.06
    POSITIVE LOGITS
    .FixedSingle
    0.06
    ленні
    0.06
    ？”↵↵
    0.06
    Canceled
    0.06
    逸
    0.06
    _OPEN
    0.06
    ifying
    0.06
    �乐
    0.06
     modelBuilder
    0.06
     Phill
    0.06
    Act Density 0.000%

    No Known Activations