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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     розвитку
    -0.07
     ích
    -0.07
     countryside
    -0.06
     düz
    -0.06
    城市
    -0.06
    内部
    -0.06
     Kale
    -0.06
     Delta
    -0.06
     развитие
    -0.06
    _in
    -0.06
    POSITIVE LOGITS
    	ip
    0.06
     doe
    0.06
    -month
    0.06
     pelic
    0.06
     Cri
    0.06
     accus
    0.06
    _PED
    0.06
    _DEAD
    0.06
     cpf
    0.06
     pinned
    0.06
    Act Density 0.020%

    No Known Activations