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

    Neuronpedia

    INDEX
    Explanations

    And

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     having
    -0.09
     kura
    -0.08
     fuck
    -0.08
    -0.08
     structs
    -0.07
     sodass
    -0.07
    ぱ
    -0.07
     indiv
    -0.07
    pard
    -0.07
     yun
    -0.07
    POSITIVE LOGITS
    Topics
    0.10
     blog
    0.09
     בנושא
    0.09
    博客
    0.09
     Topics
    0.09
    Topic
    0.08
    专题
    0.08
     ब्लॉग
    0.08
     Explore
    0.08
     посвящ
    0.08
    Act Density 0.159%
    No Known Activations