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

    Neuronpedia

    INDEX
    Explanations

    sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ystems
    -0.07
     personals
    -0.07
    писок
    -0.07
    Psi
    -0.06
    SCRIPTION
    -0.06
    SessionFactory
    -0.06
    bos
    -0.06
    ucu
    -0.06
    wendung
    -0.06
    _nsec
    -0.06
    POSITIVE LOGITS
     getPosition
    0.07
    adaki
    0.06
     привед
    0.06
    amilia
    0.06
     Tarif
    0.06
     uphe
    0.06
     معت
    0.06
     dific
    0.06
     увели
    0.06
     vel
    0.06
    Act Density 0.017%

    No Known Activations