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

    Neuronpedia

    INDEX
    Explanations

    security resources and hotlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Suggestions
    0.29
     melod
    0.28
    生理
    0.27
     vomit
    0.26
     পুজ
    0.26
     Pick
    0.25
     Sublime
    0.25
     These
    0.25
     setTheme
    0.25
     sesuai
    0.25
    POSITIVE LOGITS
    agent
    0.33
    securitycenter
    0.29
    agy
    0.29
    @[
    0.28
    aware
    0.28
    user
    0.27
     agent
    0.27
     Jawah
    0.27
    ตน
    0.26
    ಲೀ
    0.26
    Act Density 0.077%

    No Known Activations