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

    Neuronpedia

    INDEX
    Explanations

    cast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VERSE
    -0.07
     Зд
    -0.06
     популяр
    -0.06
     존
    -0.06
     giản
    -0.06
     david
    -0.06
    ⠀⠀
    -0.06
    _both
    -0.06
     Laguna
    -0.06
     yere
    -0.06
    POSITIVE LOGITS
     capitalist
    0.07
    ,C
    0.07
    (Font
    0.07
    轮
    0.07
     readiness
    0.06
     Companies
    0.06
    _ch
    0.06
     conspiracy
    0.06
    _charset
    0.06
     agreements
    0.06
    Act Density 0.005%

    No Known Activations