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

    Neuronpedia

    INDEX
    Explanations

    2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embracing
    0.35
     Developing
    0.35
     Implement
    0.32
     toroidal
    0.32
     Vary
    0.31
     Increasing
    0.31
     Leveraging
    0.31
     Develop
    0.31
     Schur
    0.31
    (!
    0.31
    POSITIVE LOGITS
    ỗ
    0.31
     સ્વા
    0.30
    <0xD5>
    0.30
    附近
    0.30
    ziert
    0.30
    vorschau
    0.30
    deutsch
    0.30
    munk
    0.30
    ５
    0.30
    στό
    0.30
    Act Density 0.050%

    No Known Activations