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

    Neuronpedia

    INDEX
    Explanations

    well-documented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disposed
    0.68
     intelligent
    0.67
     smart
    0.66
     beh
    0.65
     belangrijke
    0.65
     brilliant
    0.65
     summoned
    0.64
     read
    0.64
    asant
    0.64
    大切な
    0.64
    POSITIVE LOGITS
    Defined
    1.07
    characterized
    1.04
     document
    1.04
    defined
    1.00
     문서
    0.99
     документи
    0.99
    character
    0.99
    Document
    0.99
    Character
    0.98
    document
    0.95
    Act Density 0.068%

    No Known Activations