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

    Neuronpedia

    INDEX
    Explanations

    online shop or website

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شدن
    0.38
     रमेश
    0.37
    ลาส
    0.36
    erate
    0.36
     baseless
    0.36
    erat
    0.35
     phased
    0.35
     skeleton
    0.35
    aternary
    0.35
    르고
    0.34
    POSITIVE LOGITS
     W
    0.68
    W
    0.60
     Popular
    0.50
    Popular
    0.46
     Diseases
    0.46
     வெ
    0.45
     Medicines
    0.45
     WOL
    0.45
     Wob
    0.44
    Wol
    0.44
    Act Density 0.002%

    No Known Activations