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

    Neuronpedia

    INDEX
    Explanations

    numbers and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     फ्रेंड्स
    0.44
    时间和
    0.37
    仑
    0.35
    尽
    0.35
    明显
    0.34
    则是
    0.34
    鲜
    0.34
    矩阵
    0.34
    补
    0.34
    শি
    0.34
    POSITIVE LOGITS
     equilateral
    0.40
     kommun
    0.39
    ជ្
    0.38
    oi
    0.38
     sabia
    0.37
    getBounding
    0.37
     COMMUN
    0.37
     lete
    0.36
     subgoal
    0.36
     anastom
    0.35
    Act Density 0.014%

    No Known Activations