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

    Neuronpedia

    INDEX
    Explanations

    step angle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ैया
    0.38
     partager
    0.36
    iveau
    0.35
    잼
    0.35
    ophores
    0.35
    ลำ
    0.35
    柏
    0.35
     따라
    0.34
    危
    0.34
    க்க
    0.34
    POSITIVE LOGITS
     aerodynamic
    0.45
     electrolytic
    0.40
     roughly
    0.38
    किंग
    0.38
     ຂ
    0.38
     airtight
    0.38
     fairies
    0.37
    λιο
    0.37
     Freeze
    0.37
     магистра
    0.36
    Act Density 0.001%

    No Known Activations