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

    Neuronpedia

    INDEX
    Explanations

    NOT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kır
    -0.06
    LR
    -0.06
     lo
    -0.06
     sho
    -0.06
    .Sys
    -0.06
    DTO
    -0.06
    Writer
    -0.06
    ォ
    -0.06
    囲
    -0.06
    *ft
    -0.06
    POSITIVE LOGITS
     Bootstrap
    0.07
     struggles
    0.06
    .Misc
    0.06
    AGING
    0.06
    ovaly
    0.06
     Hash
    0.06
    Appear
    0.06
     Bullet
    0.06
    assistant
    0.06
     Garland
    0.06
    Act Density 0.003%

    No Known Activations