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

    Neuronpedia

    INDEX
    Explanations

    real estate investment and transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.55
    ה
    1.31
    ه
    1.29
    し
    1.22
    ة
    1.11
    з
    1.10
    м
    1.09
    는
    1.06
    𝚎
    1.06
    й
    1.00
    POSITIVE LOGITS
     in
    1.27
     are
    1.24
     n
    1.15
     malicious
    1.14
    0
    1.13
     y
    1.13
     an
    1.09
     d
    1.08
     osa
    1.08
     s
    1.07
    Act Density 0.006%

    No Known Activations