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

    Neuronpedia

    INDEX
    Explanations

    numbers, dates, and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ១
    0.38
     तुर
    0.37
     બાબ
    0.37
     GEO
    0.36
     전달
    0.36
     спо
    0.36
     CT
    0.35
     बादल
    0.35
    rale
    0.35
     YT
    0.35
    POSITIVE LOGITS
    自从
    0.38
    isição
    0.37
    0.37
    سبوع
    0.35
    டைந்த
    0.34
     業務用
    0.34
     بیټ
    0.34
    ציה
    0.34
     rescued
    0.34
     immunity
    0.34
    Act Density 0.035%

    No Known Activations