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

    Neuronpedia

    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oppressed
    -0.08
    _pop
    -0.07
    _lhs
    -0.07
     tổn
    -0.07
     OPER
    -0.07
    _threads
    -0.06
     Вона
    -0.06
     عم
    -0.06
     scarce
    -0.06
     violent
    -0.06
    POSITIVE LOGITS
    иг
    0.06
     env
    0.06
     clustering
    0.06
     Kl
    0.06
     vardır
    0.06
     vn
    0.06
    Mill
    0.06
     converter
    0.06
     SEO
    0.06
    덤프
    0.06
    Act Density 0.010%

    No Known Activations