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

    Neuronpedia

    INDEX
    Explanations

    treasure and associated places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    1.36
    is
    1.35
    ج
    1.30
    э
    1.29
    ف
    1.25
    س
    1.24
    к
    1.20
    ش
    1.13
    т
    1.08
    й
    1.02
    POSITIVE LOGITS
     trove
    1.32
     treasures
    1.19
     K
    1.13
     treasure
    1.13
     O
    1.08
     E
    1.05
     M
    1.05
     アップ
    1.02
     กล
    1.01
     ก
    1.00
    Act Density 0.005%

    No Known Activations