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

    Neuronpedia

    INDEX
    Explanations

    salary and experience range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wages
    0.43
     விஞ்ஞான
    0.43
     freien
    0.43
     वेतन
    0.42
     biochemical
    0.42
     Salaries
    0.41
    Income
    0.40
    னி
    0.40
     salário
    0.40
     dependant
    0.40
    POSITIVE LOGITS
     functionalities
    0.44
    odend
    0.44
     funcionalidades
    0.42
     tabletop
    0.41
    OscInitStruct
    0.39
    odendron
    0.38
    ünftig
    0.38
    raintree
    0.37
     Valent
    0.37
    带来了
    0.36
    Act Density 0.023%

    No Known Activations