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

    Neuronpedia

    INDEX
    Explanations

    expressing opinions or arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     От
    -0.07
     mood
    -0.07
    itles
    -0.07
     Ç
    -0.06
    offs
    -0.06
     rack
    -0.06
     mf
    -0.06
     traj
    -0.06
    errick
    -0.06
    career
    -0.06
    POSITIVE LOGITS
     colorWith
    0.08
    .Reflection
    0.07
     Hàn
    0.07
    篇文章
    0.07
    راه
    0.07
    蚤
    0.07
    楝
    0.07
    �
    0.07
    łó
    0.07
    RootElement
    0.07
    Act Density 0.120%

    No Known Activations