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

    Neuronpedia

    INDEX
    Explanations

    software vulnerabilities, programming, or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PROP
    0.43
     prop
    0.42
    ydın
    0.40
     hom
    0.39
    metro
    0.38
     شه
    0.38
    prop
    0.37
     Jai
    0.36
    ReadFile
    0.36
    Gur
    0.36
    POSITIVE LOGITS
    のみ
    0.37
    itaires
    0.37
     সত্ত
    0.35
     पश्चात
    0.35
    тым
    0.35
    сім
    0.35
     wisdom
    0.35
    中です
    0.34
    شارك
    0.34
    ease
    0.34
    Act Density 0.000%

    No Known Activations