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

    Neuronpedia

    INDEX
    Explanations

    Illuminate facades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    刂
    0.38
    製の
    0.38
    ֜
    0.38
    )`;
    0.37
     విజ
    0.37
     selain
    0.36
    িনা
    0.35
    耆
    0.35
    จึง
    0.35
    ޞ
    0.35
    POSITIVE LOGITS
     facade
    0.51
    Facades
    0.51
     facades
    0.47
    Message
    0.45
     message
    0.44
    message
    0.44
     faç
    0.41
     serviço
    0.41
    ounded
    0.41
    éry
    0.41
    Act Density 0.001%

    No Known Activations