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

    Neuronpedia

    INDEX
    Explanations

    addresses, dates, and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wohn
    0.47
    msch
    0.42
     Proposed
    0.39
    讲解
    0.39
    pied
    0.39
     Wohn
    0.37
     roommates
    0.37
     एवरेज
    0.37
     overloaded
    0.37
    Φ
    0.36
    POSITIVE LOGITS
     sopra
    0.42
    राइ
    0.41
     অস্ত্রের
    0.40
    数据的
    0.39
     Ago
    0.38
     abajo
    0.38
    ొ
    0.38
     ago
    0.37
     montrer
    0.37
     above
    0.37
    Act Density 0.001%

    No Known Activations