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

    Neuronpedia

    INDEX
    Explanations

    modal verbs followed by clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    1.25
    。
    1.18
     б
    1.08
    ۔
    1.05
    т
    1.04
    ের
    1.00
    sPath
    0.99
    ével
    0.98
    ًا
    0.98
    。\
    0.97
    POSITIVE LOGITS
    la
    0.99
     CON
    0.93
    lu
    0.92
     secrecy
    0.90
     Deborah
    0.89
    和服务
    0.87
     C
    0.86
    لى
    0.86
    惇
    0.86
    INT
    0.83
    Act Density 1.442%

    No Known Activations