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

    Neuronpedia

    INDEX
    Explanations

    you're right to seek

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डिली
    0.47
    は
    0.47
     lecture
    0.46
     dwellers
    0.45
     designers
    0.43
     cushioning
    0.43
     hå
    0.42
     plumber
    0.42
     hår
    0.42
     तस्करी
    0.41
    POSITIVE LOGITS
    outed
    0.52
     ಅನ
    0.45
    集合
    0.45
    sType
    0.45
    ory
    0.44
    getResult
    0.44
     ailes
    0.44
    ά
    0.44
    o
    0.43
    ή
    0.43
    Act Density 0.003%

    No Known Activations