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

    Neuronpedia

    INDEX
    Explanations

    multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Employee
    0.43
    केल
    0.43
     DevOps
    0.42
     MongoDB
    0.42
    云计算
    0.42
    ระ
    0.41
    Tenant
    0.41
     নিয়োগ
    0.41
     Developer
    0.40
     Kubernetes
    0.40
    POSITIVE LOGITS
    Reli
    0.36
     center
    0.34
     عج
    0.34
     papeles
    0.34
     reliable
    0.33
     ds
    0.33
    divisor
    0.33
     એટ
    0.32
     Nxf
    0.31
     स्तरीय
    0.31
    Act Density 0.000%

    No Known Activations