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

    Neuronpedia

    INDEX
    Explanations

    mathematical framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilerinin
    1.42
    鑊
    1.42
    牒
    1.37
    kere
    1.37
    ุ้น
    1.34
    corsi
    1.32
    estones
    1.31
     futhi
    1.30
    ilerine
    1.30
    çons
    1.29
    POSITIVE LOGITS
     Gaston
    1.87
    Entities
    1.72
     chatbot
    1.58
     humanoid
    1.52
     Alessandro
    1.52
     Samantha
    1.49
     Gemma
    1.48
     Entities
    1.48
    植物
    1.48
     Hew
    1.47
    Act Density 0.330%

    No Known Activations