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

    Neuronpedia

    INDEX
    Explanations

    web pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     web
    0.54
     Web
    0.53
    Web
    0.50
     वेब
    0.49
    web
    0.46
     WEB
    0.46
     webs
    0.46
     веб
    0.44
    웹
    0.44
    ANG
    0.43
    POSITIVE LOGITS
    刎
    0.42
    שה
    0.40
     resentment
    0.39
     abre
    0.39
    تبع
    0.37
    poetrylovers
    0.37
     forgiven
    0.36
     Cere
    0.36
    струк
    0.36
     Armen
    0.36
    Act Density 0.004%

    No Known Activations