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

    Neuronpedia

    INDEX
    Explanations

    health or government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OGND
    -0.71
    InjectAttribute
    -0.68
    原始内容存档于
    -0.66
    ThroughAttribute
    -0.60
    شهاد
    -0.60
    IsContent
    -0.59
    mybatisplus
    -0.59
    expandindo
    -0.59
    ReusableCell
    -0.58
    ValueStyle
    -0.57
    POSITIVE LOGITS
    ebvre
    0.63
    ReadLine
    0.59
    AddTagHelper
    0.56
     cuts
    0.52
    GLint
    0.52
    msgSender
    0.50
    TMR
    0.48
     *((
    0.48
    Descriptions
    0.47
     cut
    0.47
    Act Density 0.041%

    No Known Activations