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

    Neuronpedia

    INDEX
    Explanations

    months and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onboarding
    0.36
     dépos
    0.33
     coffers
    0.32
     workflow
    0.31
     acol
    0.31
     KPIs
    0.31
     foodie
    0.31
     SLAs
    0.30
     confid
    0.30
     bullies
    0.30
    POSITIVE LOGITS
    ７
    0.35
    工業
    0.34
    Czechoslovakia
    0.34
    🔟
    0.34
    7
    0.33
    𝟭
    0.33
     अप्रैल
    0.32
    ১৭
    0.32
     அமெரிக்க
    0.31
     ১৯৬
    0.31
    Act Density 0.037%

    No Known Activations