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

    Neuronpedia

    INDEX
    Explanations

    target followed by specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     まとめ
    0.97
    יים
    0.93
    żeli
    0.88
    borhood
    0.87
    좁
    0.86
     Inbox
    0.86
     textField
    0.85
    qn
    0.85
    sion
    0.84
    ്
    0.83
    POSITIVE LOGITS
    érateur
    0.93
    ع
    0.91
     continuer
    0.88
    ная
    0.86
     alvo
    0.85
     thước
    0.81
     brauchen
    0.81
     ausgestattet
    0.80
     луч
    0.79
    oured
    0.79
    Act Density 0.111%

    No Known Activations