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

    Neuronpedia

    INDEX
    Explanations

    evaluation: score : difficulty :

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.39
    7
    0.38
    threat
    0.37
    로드
    0.37
     kolem
    0.36
    1
    0.35
    ær
    0.35
    สวย
    0.35
    killing
    0.34
    ۷
    0.34
    POSITIVE LOGITS
     cũng
    0.40
     أيضًا
    0.38
     similarly
    0.38
     asimismo
    0.37
     dùng
    0.36
     nếu
    0.36
    也會
    0.36
     እንዲሁ
    0.36
     যদি
    0.35
    যদি
    0.35
    Act Density 0.046%

    No Known Activations