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

    Neuronpedia

    INDEX
    Explanations

    document management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     đầu
    0.28
     Mt
    0.27
     cash
    0.27
     waterfront
    0.26
     eyeliner
    0.26
     intestines
    0.26
     login
    0.25
     lemonade
    0.25
     lu
    0.25
     hydrant
    0.25
    POSITIVE LOGITS
    ೬
    0.37
    ៤
    0.36
     관련
    0.35
     제한
    0.35
    ี
    0.34
     рези
    0.34
    இந்த
    0.34
    倞
    0.33
    א
    0.33
    0.33
    Act Density 0.239%

    No Known Activations