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

    Neuronpedia

    INDEX
    Explanations

    basis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whispered
    -0.07
    Federal
    -0.07
     Coord
    -0.07
     analyst
    -0.06
     ăn
    -0.06
    commit
    -0.06
    _HEALTH
    -0.06
    Hand
    -0.06
    .beginTransaction
    -0.06
     Room
    -0.06
    POSITIVE LOGITS
     nejd
    0.06
     хви
    0.06
     ژانویه
    0.06
     противоп
    0.06
    στη
    0.06
    Я
    0.06
     좋
    0.06
    DY
    0.06
    transaction
    0.06
    젤
    0.06
    Act Density 0.001%

    No Known Activations