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

    Neuronpedia

    INDEX
    Explanations

    [@

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    db
    -0.07
     Subset
    -0.07
     teaches
    -0.07
     reduced
    -0.07
     anytime
    -0.07
     Baby
    -0.07
     additions
    -0.07
     meals
    -0.07
     project
    -0.07
     projects
    -0.07
    POSITIVE LOGITS
    tfoot
    0.06
    不是
    0.06
    олош
    0.06
    .WriteString
    0.06
    ：</
    0.06
    .bulk
    0.06
    .urlopen
    0.05
     země
    0.05
     ニ
    0.05
    CAA
    0.05
    Act Density 0.005%

    No Known Activations