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

    Neuronpedia

    INDEX
    Explanations

    requesting user information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isAuthenticated
    0.44
     Authentication
    0.41
     jika
    0.41
    Authentication
    0.39
     Assessments
    0.39
    authent
    0.38
     هنا
    0.38
     thePack
    0.38
     iner
    0.38
     asalamualaikum
    0.37
    POSITIVE LOGITS
    Tell
    0.48
     tell
    0.48
     Tell
    0.48
     TELL
    0.47
     give
    0.43
    tell
    0.42
    give
    0.42
    Give
    0.41
     Give
    0.40
    告诉
    0.39
    Act Density 0.007%

    No Known Activations