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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stabilized
    -0.27
    ç®±
    -0.27
     discrimin
    -0.27
    wig
    -0.27
     overwhel
    -0.27
     disappeared
    -0.26
    ulative
    -0.25
    å¹´çĶ±
    -0.25
     distributes
    -0.25
    çļĦ身份
    -0.24
    POSITIVE LOGITS
    OWER
    0.27
    -opacity
    0.26
    æ¸Ĭ
    0.26
    åĪĩ
    0.25
    aunch
    0.25
    äºĭå®ľ
    0.25
    ropa
    0.25
     matter
    0.24
     siden
    0.24
    ç¼
    0.24
    Act Density 0.003%

    No Known Activations