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

    Neuronpedia

    INDEX
    Explanations

    CI/CD automation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Accordingly
    0.47
     পুরো
    0.43
    るので
    0.39
    니까
    0.38
     изначально
    0.37
    였습니다
    0.37
    ል።
    0.37
     dichotomy
    0.37
     धक्का
    0.36
     ønsk
    0.36
    POSITIVE LOGITS
    alg
    0.37
    backup
    0.36
    archive
    0.34
    வாச
    0.34
    ook
    0.34
    sor
    0.33
    访问
    0.33
    新增
    0.33
    uid
    0.33
    વાસ
    0.32
    Act Density 0.010%

    No Known Activations