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

    Neuronpedia

    INDEX
    Explanations

    Characteristics/personality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deal
    -0.07
    飞船
    -0.06
     obsession
    -0.06
    来た
    -0.06
    帝王
    -0.06
    .getState
    -0.06
     NAFTA
    -0.06
     ;
↵
    -0.06
    LB
    -0.06
     orc
    -0.06
    POSITIVE LOGITS
     cured
    0.08
    breadcrumbs
    0.08
    modules
    0.07
    勾
    0.07
    _emails
    0.07
    template
    0.07
     firmware
    0.07
    pixels
    0.07
    账户
    0.07
    anan
    0.07
    Act Density 0.107%

    No Known Activations