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

    Neuronpedia

    INDEX
    Explanations

    multiple languages and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.37
    ه
    0.37
    i
    0.36
    FocusValue
    0.35
    م
    0.35
    ش
    0.35
     én
    0.34
     étudiants
    0.33
     carénés
    0.33
     oats
    0.32
    POSITIVE LOGITS
    もあります
    0.30
     못한
    0.29
       
    0.27
    などの
    0.27
    о
    0.27
    ｱ
    0.27
    以外の
    0.27
    ；
    0.27
    ↵
    0.27
     lurking
    0.26
    Act Density 0.137%

    No Known Activations