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

    Neuronpedia

    INDEX
    Explanations

    named entities and AI

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Allowed
    0.58
     occup
    0.56
     lashes
    0.56
    yaj
    0.56
     Height
    0.55
     myList
    0.55
     Bub
    0.54
     لیتے
    0.54
     कुशलता
    0.53
    кл
    0.52
    POSITIVE LOGITS
     चौधरी
    0.55
     генера
    0.54
    Ҭ
    0.51
     Ozzy
    0.51
    Bened
    0.50
     Publishers
    0.50
    quartered
    0.50
    Register
    0.49
     Edgar
    0.49
    гістра
    0.49
    Act Density 0.000%

    No Known Activations