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

    Neuronpedia

    INDEX
    Explanations

    IT backlogs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hábito
    0.41
     elektromagnet
    0.40
     prefers
    0.40
     আর্ক
    0.40
     Arth
    0.39
     Resonance
    0.38
    ofil
    0.38
     prefer
    0.38
    多么
    0.37
     kült
    0.37
    POSITIVE LOGITS
     (\"
    0.39
     -"
    0.39
    дачи
    0.38
    ⑹
    0.38
     \"
    0.38
    (“
    0.37
     ("
    0.37
     (“
    0.36
     load
    0.36
     aisément
    0.36
    Act Density 0.000%

    No Known Activations