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

    Neuronpedia

    INDEX
    Explanations

    Author initials and last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ๎
    0.43
     вто
    0.43
     ус
    0.41
    uch
    0.40
    ine
    0.40
    ling
    0.40
    oppel
    0.39
     volatile
    0.36
    cox
    0.36
    льзя
    0.36
    POSITIVE LOGITS
    Bollywood
    0.52
    ﺍ
    0.50
    𝖺
    0.50
     Tutti
    0.48
    𝚊
    0.47
     détails
    0.46
    الم
    0.45
     piernas
    0.45
    המ
    0.45
     realises
    0.44
    Act Density 0.002%

    No Known Activations