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

    Neuronpedia

    INDEX
    Explanations

    Math questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    63
    -0.07
     >
    -0.07
     disks
    -0.07
     competitor
    -0.06
    ":↵
    -0.06
     preparing
    -0.06
     demanding
    -0.06
     discs
    -0.06
    "],
    -0.06
     invers
    -0.06
    POSITIVE LOGITS
    ez
    0.07
     Income
    0.07
    َّ
    0.06
     Thirty
    0.06
    َّ
    0.06
     Bakan
    0.06
    лександ
    0.06
    �
    0.06
     جمع
    0.06
     NSInteger
    0.06
    Act Density 0.005%

    No Known Activations