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

    Neuronpedia

    INDEX
    Explanations

    guns/rifles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NSA
    -0.08
    ублі
    -0.07
     dinero
    -0.07
     человек
    -0.07
    ан
    -0.06
     Alta
    -0.06
    ІІ
    -0.06
    다면
    -0.06
    ρος
    -0.06
    мы
    -0.06
    POSITIVE LOGITS
     bufio
    0.07
     üz
    0.06
    _bh
    0.06
     Cool
    0.06
    说明
    0.06
    etration
    0.06
     Exercises
    0.06
     Rooney
    0.06
    laws
    0.05
     motivations
    0.05
    Act Density 0.011%

    No Known Activations